© 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. 31-TRANSCODER-HP
    7. 18277
    Prev
    Next
    INDEX
    Explanations

    example

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imity
    -0.27
    oks
    -0.26
    ongs
    -0.26
    onor
    -0.25
    angles
    -0.25
    rost
    -0.25
     Tam
    -0.25
    ules
    -0.25
    chu
    -0.25
    ç§ĺ书
    -0.24
    POSITIVE LOGITS
     problem
    0.43
    éĹ®é¢ĺ
    0.33
     assumption
    0.31
     example
    0.30
    problem
    0.29
     adaptation
    0.29
     sample
    0.28
    åģĩ
    0.28
     Problem
    0.28
     transmission
    0.28
    Activations Density 0.037%

    No Known Activations