© 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. 5400
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    èĩªæĿ¥
    -0.29
    çīĻ
    -0.28
     tree
    -0.27
    èĬ½
    -0.26
    nea
    -0.26
    代表æĢ§
    -0.26
    è¿ĵ
    -0.26
    stood
    -0.25
    intree
    -0.25
    éĢģæĿ¥
    -0.25
    POSITIVE LOGITS
    åIJīæŀĹçľģ
    0.28
    Corp
    0.27
    POL
    0.26
     quyết
    0.26
     recomend
    0.26
    rob
    0.25
    (origin
    0.25
    onyms
    0.24
    logical
    0.24
    plete
    0.24
    Activations Density 0.634%

    No Known Activations