© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42108
    Prev
    Next
    INDEX
    Explanations

    technology product headlines/reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ©
    -0.30
     ============================================================================↵
    -0.26
    çİĩåħĪ
    -0.25
     retros
    -0.24
     DataTypes
    -0.24
    .linalg
    -0.24
    ãĤ¿ãĥ¼
    -0.24
    ç§ĥ
    -0.24
    ale
    -0.23
    ]%
    -0.23
    POSITIVE LOGITS
    .flash
    0.26
    åįģ
    0.26
    лив
    0.25
     Rehab
    0.25
    éİı
    0.25
     Eleven
    0.25
    èĥĮçĿĢ
    0.25
     Encode
    0.25
    encil
    0.24
    adia
    0.24
    Activations Density 0.031%

    No Known Activations