© 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. 162391
    Prev
    Next
    INDEX
    Explanations

    Personal anecdotes

    np_max-act · gemini-2.0-flash
    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
    atz
    -0.28
    &e
    -0.26
    ire
    -0.26
    odo
    -0.25
     buffering
    -0.25
    iers
    -0.25
    bish
    -0.24
     Beer
    -0.24
     irr
    -0.24
    rir
    -0.23
    POSITIVE LOGITS
    æİĮæı¡äºĨ
    0.32
    æĭįæĭį
    0.28
    vided
    0.26
    æĢĻ
    0.26
    éĥ¨ä¸»ä»»
    0.26
    ç´¯äºĨ
    0.25
    æ¯ıä¸Ģ个
    0.25
    åĴĮæĶ¯æĮģ
    0.25
    æݥ触åĪ°
    0.25
    åıĤä¸İåĪ°
    0.25
    Activations Density 0.008%

    No Known Activations