Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 3083
    Prev
    Next
    INDEX
    Explanations

    Negative consequences or effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inally
    -0.26
    goal
    -0.25
    .getMethod
    -0.25
    羣çIJĨ
    -0.24
     obr
    -0.24
     garlic
    -0.24
     goal
    -0.24
    Goal
    -0.24
     sol
    -0.24
    elta
    -0.24
    POSITIVE LOGITS
     severity
    0.34
    伤害
    0.32
    severity
    0.29
    çł´åĿı
    0.28
    大åıij
    0.28
     wreak
    0.28
     Severity
    0.27
    èĢ½è¯¯
    0.27
    éĶĻè¿ĩ
    0.27
    æ¯ģçģŃ
    0.27
    Activations Density 0.002%

    No Known Activations