© 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. 32-TRANSCODER-HP
    7. 44152
    Prev
    Next
    INDEX
    Explanations

    intern

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ied
    -0.27
     Uruguay
    -0.25
    -wow
    -0.24
    娩
    -0.24
    IED
    -0.24
    ery
    -0.24
     squeeze
    -0.24
    .Lines
    -0.24
    éĻ¤å°ĺ
    -0.23
     sour
    -0.23
    POSITIVE LOGITS
    ista
    0.30
    als
    0.28
    itr
    0.28
    engl
    0.28
    çī¹
    0.27
    onaut
    0.26
     acos
    0.25
    ships
    0.25
    oods
    0.25
    åħĭæĸ¯
    0.25
    Activations Density 0.002%

    No Known Activations