© 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. 27-TRANSCODER-HP
    7. 58513
    Prev
    Next
    INDEX
    Explanations

    fishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĨĴéĻ©
    -0.26
     gymn
    -0.25
    IPS
    -0.24
    InstanceState
    -0.24
    mad
    -0.24
    á»įng
    -0.24
    (inplace
    -0.24
    ока
    -0.24
    è´¨éĩı管çIJĨ
    -0.23
    ç¥ĵ
    -0.23
    POSITIVE LOGITS
     towers
    0.27
     halls
    0.27
    人群ä¸Ń
    0.27
     communities
    0.26
    åľĪåŃIJ
    0.25
     triangles
    0.25
     community
    0.25
     traps
    0.25
    uez
    0.24
    è¿Ļ座
    0.24
    Activations Density 0.041%

    No Known Activations