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. 7-TRANSCODER-HP
    4. 24121
    Prev
    Next
    INDEX
    Explanations

    "blow"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outed
    -0.27
    UBL
    -0.27
    _DISPATCH
    -0.26
    ода
    -0.26
    çº
    -0.25
     lod
    -0.25
    ingles
    -0.24
    -enter
    -0.24
    ghan
    -0.24
    igue
    -0.24
    POSITIVE LOGITS
    åĪĨ级
    0.26
    èĩ´çĻĮ
    0.25
     Adresse
    0.25
    ç¾İ女
    0.25
     Slo
    0.24
    æ¡ģ
    0.24
    ociety
    0.23
    å®ģå¤ı
    0.23
    åĬĽè¿ĺæĺ¯
    0.23
     Alicia
    0.23
    Activations Density 0.001%

    No Known Activations