© 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. 5360
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æµ£
    -0.29
    åģļä¸įåĪ°
    -0.26
    å¤ļæł·
    -0.26
    åħ±
    -0.26
    ATIVE
    -0.26
    åı¦ä¸Ģç§į
    -0.25
    äºĪ
    -0.25
    ategorical
    -0.25
    涯
    -0.25
     purpos
    -0.25
    POSITIVE LOGITS
    indle
    0.28
    <small
    0.26
     sinks
    0.25
     sic
    0.24
     secure
    0.24
    ç§ĭåĨ¬
    0.24
    ?(:
    0.24
     securely
    0.24
    idia
    0.24
    ä¸ĵåĮº
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.