© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40780
    Prev
    Next
    INDEX
    Explanations

    github

    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
    Negative Logits
     exceptions
    -0.28
     JSON
    -0.27
     illustr
    -0.27
     indexes
    -0.26
     exports
    -0.25
     folders
    -0.25
     manifests
    -0.25
     validations
    -0.24
     integers
    -0.24
     others
    -0.24
    POSITIVE LOGITS
    /inc
    0.31
    ."\
    0.29
    /color
    0.28
    /buttons
    0.28
    /pi
    0.28
    -neck
    0.28
    /internal
    0.28
    /legal
    0.27
    /stdc
    0.27
    .^
    0.27
    Activations Density 37.879%

    No Known Activations