© 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. 42430
    Prev
    Next
    INDEX
    Explanations

    Lanc

    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
    æ±°
    -0.28
    dÃŃ
    -0.27
    åŃIJå¼¹
    -0.26
    çī¯
    -0.26
     Leader
    -0.25
    .priv
    -0.24
    éal
    -0.24
    é«»
    -0.24
    ewire
    -0.24
    cook
    -0.24
    POSITIVE LOGITS
    icide
    0.29
    rost
    0.28
    æľĹ诵
    0.26
    um
    0.25
    berman
    0.25
    antine
    0.25
    顺çĿĢ
    0.25
    otto
    0.25
    æī³
    0.25
     campuses
    0.24
    Activations Density 0.002%

    No Known Activations