© 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. 5755
    Prev
    Next
    INDEX
    Explanations

    complication

    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
    纵深
    -0.24
    å¹ķåIJİ
    -0.22
    Traits
    -0.22
    å»ĬåĿĬ
    -0.21
    çļĦéĤ£ç§į
    -0.21
     Portions
    -0.21
    ä¸Ģæĸ¹
    -0.21
    è¿Ļç§įæĸ¹å¼ı
    -0.21
    äl
    -0.21
    ambre
    -0.21
    POSITIVE LOGITS
    atisf
    0.25
    akes
    0.25
    plete
    0.24
    plies
    0.24
     matters
    0.23
    suming
    0.23
    omen
    0.23
    sector
    0.22
    era
    0.22
    urge
    0.22
    Activations Density 1.802%

    No Known Activations