© 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. 58268
    Prev
    Next
    INDEX
    Explanations

    Negative events and code snippets

    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
    åį±å®³
    -0.65
    å¨ģèĥģ
    -0.63
     affecting
    -0.63
    害
    -0.61
    å½±åĵį
    -0.61
     impacting
    -0.57
    çļĦåį±å®³
    -0.56
     impact
    -0.54
     affects
    -0.54
     threatening
    -0.53
    POSITIVE LOGITS
     expired
    0.27
    uros
    0.26
    isos
    0.26
     Naked
    0.26
    edException
    0.25
     fail
    0.25
    unft
    0.24
    è¯ŀ
    0.24
    fail
    0.24
     Pee
    0.24
    Activations Density 0.002%

    No Known Activations