© 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. 9570
    Prev
    Next
    INDEX
    Explanations

    programming and software questions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    oste
    -0.27
     otherwise
    -0.27
    çĦ¶æĺ¯
    -0.26
     Otherwise
    -0.25
     Erot
    -0.25
    asis
    -0.25
    verts
    -0.25
    带çĿĢ
    -0.25
    steen
    -0.25
    oe
    -0.25
    POSITIVE LOGITS
    ascript
    0.28
    duced
    0.27
    RESSED
    0.26
    åIJĪåIJĮ
    0.25
    åĬŀäºĭ
    0.25
    ntl
    0.25
     toy
    0.24
     script
    0.24
    igraph
    0.24
     GetHashCode
    0.24
    Activations Density 0.004%

    No Known Activations