© 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. 44262
    Prev
    Next
    INDEX
    Explanations

    P

    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
    饺åŃIJ
    -0.29
    æľīæĦı
    -0.27
    责任åĪ¶
    -0.25
    apy
    -0.24
    æ°¡
    -0.24
     ion
    -0.23
    /he
    -0.23
    mdir
    -0.23
    gary
    -0.23
    cury
    -0.23
    POSITIVE LOGITS
    onda
    0.31
    quisite
    0.28
    OSH
    0.26
    quiv
    0.26
    azon
    0.26
    quisites
    0.26
    eos
    0.25
    åĩº
    0.25
    conomic
    0.25
    лиÑģÑĤ
    0.23
    Activations Density 0.002%

    No Known Activations