© 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. 7878
    Prev
    Next
    INDEX
    Explanations

    -income

    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
     Neutral
    -0.28
     Wheels
    -0.27
     bullets
    -0.26
     wheels
    -0.25
    etta
    -0.25
    teen
    -0.24
    atsby
    -0.24
    亿åIJ¨
    -0.24
    åĪºæ¿Ģ
    -0.24
    heels
    -0.23
    POSITIVE LOGITS
     ÑģÑĤаÑĢ
    0.30
    éĻ©
    0.27
     hại
    0.26
    è¾Ľ
    0.26
     extern
    0.26
    leveland
    0.26
     outer
    0.26
    å²Ń
    0.25
    outer
    0.25
    pragma
    0.24
    Activations Density 0.007%

    No Known Activations