© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
    å®ŀä½ĵ
    -0.28
    æ¨Ĭ
    -0.28
     paperback
    -0.27
    EXTERN
    -0.27
    ENTITY
    -0.27
     kosten
    -0.26
    .appspot
    -0.26
    айн
    -0.25
    RANDOM
    -0.25
    leitung
    -0.25
    POSITIVE LOGITS
    .setParent
    0.26
    æĶ¾æīĭ
    0.25
    设å®ļ
    0.25
    åĴĦ
    0.25
    .transitions
    0.24
    ÑģÑĭ
    0.24
    DbType
    0.23
    .Native
    0.23
    ä¸į让
    0.23
     ÑĥÑĢов
    0.23
    Activations Density 0.010%

    No Known Activations