© 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. 14-TRANSCODER-HP
    7. 39716
    Prev
    Next
    INDEX
    Explanations

    Interview questions/answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asking
    -0.32
     asking
    -0.31
     asks
    -0.27
     probing
    -0.26
    询éĹ®
    -0.26
     IMO
    -0.25
    éĹ®éģĵ
    -0.25
     fog
    -0.24
    (fe
    -0.24
    没è§ģè¿ĩ
    -0.24
    POSITIVE LOGITS
    _residual
    0.27
    æİĴ
    0.27
    ä¸įå®Į
    0.27
    èį£èªī称åı·
    0.26
    uk
    0.26
    che
    0.25
    Meet
    0.25
    HTTPHeader
    0.24
    oui
    0.24
    <?↵
    0.24
    Activations Density 0.202%

    No Known Activations