© 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. 40965
    Prev
    Next
    INDEX
    Explanations

    reach

    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
    wire
    -0.29
    ques
    -0.27
    awl
    -0.26
    avl
    -0.26
    秩
    -0.26
     Allocator
    -0.25
    hai
    -0.25
    peater
    -0.24
    war
    -0.24
     ATK
    -0.24
    POSITIVE LOGITS
     pub
    0.28
     eating
    0.27
     sexual
    0.26
    øj
    0.26
     invariant
    0.26
     intern
    0.25
    é¤
    0.25
     final
    0.25
    ctr
    0.25
     rejo
    0.24
    Activations Density 0.001%

    No Known Activations