© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5762
    Prev
    Next
    INDEX
    Explanations

    variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .firebaseapp
    -0.28
     piss
    -0.28
    pst
    -0.26
    pret
    -0.26
    onis
    -0.25
    .qq
    -0.25
    ;z
    -0.24
    åĪģ
    -0.24
    poss
    -0.24
     oss
    -0.24
    POSITIVE LOGITS
    anda
    0.26
    æ´ĭ
    0.26
    atively
    0.24
    对æİ¥
    0.24
     waived
    0.24
     abund
    0.24
    uben
    0.24
    _except
    0.23
    _prime
    0.23
     foreign
    0.23
    Activations Density 0.017%

    No Known Activations