© 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. 31-TRANSCODER-HP
    7. 17997
    Prev
    Next
    INDEX
    Explanations

    academic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çİ°
    -0.28
     scre
    -0.25
    ä¿¡
    -0.25
    rog
    -0.25
    .mm
    -0.24
    +B
    -0.24
     giá»įng
    -0.24
    åļ¼
    -0.24
     anonym
    -0.23
    ocop
    -0.23
    POSITIVE LOGITS
     enth
    0.29
    @hotmail
    0.27
    åIJģ
    0.27
    ety
    0.26
    Eth
    0.26
    ela
    0.25
    lander
    0.25
    伶
    0.25
    iliary
    0.25
    å·§å¦Ļ
    0.25
    Activations Density 0.122%

    No Known Activations