© 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. 39997
    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
    _Pods
    -0.42
    .SimpleButton
    -0.36
    mPid
    -0.34
    :UIControl
    -0.33
    åij½
    -0.32
    æĸ°
    -0.32
    éĥ½
    -0.32
    æľī
    -0.32
    PropertyParams
    -0.32
    æľĢ
    -0.31
    POSITIVE LOGITS
    _in
    0.31
    _IN
    0.31
    ov
    0.31
    Earlier
    0.31
    _R
    0.30
    _B
    0.29
     briefly
    0.29
    Result
    0.29
    _v
    0.29
    _L
    0.29
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.