© 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. 35-TRANSCODER-HP
    7. 39593
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ableObject
    -0.26
     Mirage
    -0.26
    arget
    -0.25
    áveis
    -0.25
    ilee
    -0.25
    åľ°çIJĥ
    -0.24
    Ñħ
    -0.24
    ictim
    -0.24
    еÑĢ
    -0.24
    yer
    -0.24
    POSITIVE LOGITS
    /OR
    0.28
    odore
    0.27
    ore
    0.26
     more
    0.26
    _kw
    0.26
    &t
    0.25
     absolutely
    0.25
     anth
    0.25
     latter
    0.24
    stag
    0.24
    Activations Density 0.125%

    No Known Activations