© 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. 5340
    Prev
    Next
    INDEX
    Explanations

    aisy

    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
    \modules
    -0.28
    rch
    -0.26
     hors
    -0.26
    (CONT
    -0.25
    áticas
    -0.25
    åĬŀæ³ķ
    -0.24
    ankan
    -0.24
    _clause
    -0.24
    iode
    -0.24
    atatype
    -0.23
    POSITIVE LOGITS
    ourg
    0.26
    otoxic
    0.25
    ãģĹãĤĪãģĨãģ¨
    0.25
     dictated
    0.25
    _behavior
    0.24
    对åŃ©åŃIJ
    0.24
    dir
    0.24
     gì
    0.23
     ratings
    0.23
    æľīçĽĬ
    0.23
    Activations Density 0.011%

    No Known Activations