© 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. 40164
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    *l
    -0.35
    {l
    -0.33
     l
    -0.33
    l
    -0.31
    ?t
    -0.30
     {?
    -0.29
    :l
    -0.28
    >').
    -0.28
    *t
    -0.28
     ln
    -0.27
    POSITIVE LOGITS
    çĹĪ
    0.28
    MI
    0.26
    olia
    0.25
     MILL
    0.24
    COM
    0.24
    uckle
    0.24
     Colbert
    0.24
    åºĦ
    0.24
     rainy
    0.24
    cers
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.