© 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. 44068
    Prev
    Next
    INDEX
    Explanations

    Locations around the world

    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
    selector
    -0.25
    _selector
    -0.25
    endale
    -0.25
     selectors
    -0.25
    onta
    -0.24
    éħ·
    -0.24
    .kr
    -0.24
    ümüz
    -0.24
    oenix
    -0.23
     rawData
    -0.23
    POSITIVE LOGITS
    icamente
    0.34
    Mission
    0.33
    ç»ĵåIJĪ
    0.29
    ccion
    0.28
     Mission
    0.27
    иÑĪ
    0.27
    iban
    0.27
    mal
    0.27
     Mana
    0.27
    resse
    0.26
    Activations Density 0.002%

    No Known Activations