© 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. 40843
    Prev
    Next
    INDEX
    Explanations

    Anatomical/positional descriptions

    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
    è¯
    -0.28
    érica
    -0.28
     tre
    -0.28
    çļĦè·Ŀ离
    -0.27
    çī¹æĸ¯
    -0.27
    gere
    -0.27
    shell
    -0.26
    TextLabel
    -0.26
    å¾ħ
    -0.26
    eer
    -0.25
    POSITIVE LOGITS
    antee
    0.28
    ant
    0.26
    anguard
    0.26
     Ange
    0.26
    antly
    0.25
     coalition
    0.25
    atomy
    0.24
    agal
    0.24
     Band
    0.24
    åĪ¶
    0.24
    Activations Density 0.003%

    No Known Activations