© 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. 33-TRANSCODER-HP
    7. 53337
    Prev
    Next
    INDEX
    Explanations

    third

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Drops
    -0.28
    opsis
    -0.27
     ReturnType
    -0.26
    creens
    -0.25
    “She
    -0.25
    AYS
    -0.25
    atica
    -0.24
    .clips
    -0.24
    áticas
    -0.24
    ','"+
    -0.24
    POSITIVE LOGITS
     quarter
    0.33
     wheel
    0.32
     month
    0.32
    -two
    0.32
     port
    0.31
     cone
    0.31
    -pr
    0.31
     booth
    0.31
     arrow
    0.30
     path
    0.30
    Activations Density 0.018%

    No Known Activations