© 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. 5958
    Prev
    Next
    INDEX
    Explanations

    Dashes and colons

    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
    APTER
    -0.27
    ç¼Ģ
    -0.24
    icus
    -0.24
    olume
    -0.24
     Fare
    -0.23
    iero
    -0.23
    LETE
    -0.23
    åīŁ
    -0.23
    åĬ±
    -0.23
    oris
    -0.23
    POSITIVE LOGITS
     tab
    0.30
    ;</
    0.29
    things
    0.27
    buie
    0.25
    </
    0.25
     pen
    0.24
     things
    0.24
    mon
    0.24
    bur
    0.24
     reckon
    0.24
    Activations Density 0.085%

    No Known Activations