© 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. 24-TRANSCODER-HP
    7. 151074
    Prev
    Next
    INDEX
    Explanations

    code injection/vulnerabilities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utex
    -0.26
    uben
    -0.26
    çķħéĶĢ
    -0.25
    ä¸ĬæĬ¥
    -0.25
    _HOT
    -0.25
     unpopular
    -0.25
     haber
    -0.24
     getClient
    -0.24
    icher
    -0.24
    migration
    -0.24
    POSITIVE LOGITS
    ÑģÑĤÑĢой
    0.31
     extremes
    0.26
     mid
    0.25
    ÑıÑīиÑħ
    0.25
     impulses
    0.25
     cú
    0.24
    åIJİéĿ¢çļĦ
    0.24
     extreme
    0.24
    ated
    0.24
    ATED
    0.24
    Activations Density 0.124%

    No Known Activations