© 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. 23-TRANSCODER-HP
    7. 163412
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼¹
    -0.25
    æ¯Ķäºļ
    -0.25
     Neg
    -0.24
    ifact
    -0.24
    orer
    -0.24
    isode
    -0.24
    otify
    -0.24
    ળ
    -0.24
     stream
    -0.23
    æīĢ说çļĦ
    -0.23
    POSITIVE LOGITS
    æĺ¼å¤ľ
    0.28
    ServletContext
    0.26
     RIP
    0.25
     concurrently
    0.25
    ëĭī
    0.24
    åĴ¯
    0.24
    çĥ¬
    0.24
    -Smith
    0.24
    æ¦Ĥ
    0.23
    è¹Ī
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.