© 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. 5742
    Prev
    Next
    INDEX
    Explanations

    Cell/bone turnover and regeneration

    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
     re
    -0.30
    èĢĮåıĪ
    -0.29
    Pers
    -0.27
    éĴŀ
    -0.26
    pers
    -0.26
    åį´åıĪ
    -0.26
     Cas
    -0.26
    è¾ĥå¤ļ
    -0.26
    -0.26
     cas
    -0.26
    POSITIVE LOGITS
    ilder
    0.27
     Infantry
    0.25
     smelled
    0.25
    -fi
    0.25
    Sharper
    0.24
     кÑĢÑĥ
    0.23
    ONENT
    0.23
    IODevice
    0.23
    èĤļåŃIJ
    0.23
    intColor
    0.23
    Activations Density 0.789%

    No Known Activations