© 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. 5375
    Prev
    Next
    INDEX
    Explanations

    sciences

    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
    gere
    -0.27
    人æµģ
    -0.25
    iren
    -0.25
    VIP
    -0.24
    onz
    -0.24
    ono
    -0.24
    æݨèįIJ
    -0.24
    'Ãł
    -0.24
    -know
    -0.23
     weakest
    -0.23
    POSITIVE LOGITS
    lar
    0.25
    CompanyName
    0.24
    /scripts
    0.23
    Õµ
    0.23
    è¶ĭäºİ
    0.23
     continuity
    0.23
     hub
    0.23
    scripts
    0.23
    -wow
    0.23
    ç³ĸå°¿
    0.23
    Activations Density 0.005%

    No Known Activations