© 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. 163493
    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
     RID
    -0.29
    ç¨ĭ度
    -0.28
    оÑģÑĤÑĮ
    -0.27
     Crew
    -0.26
    -payment
    -0.26
    олов
    -0.25
    ingly
    -0.25
    oor
    -0.25
     genesis
    -0.25
    qua
    -0.24
    POSITIVE LOGITS
     ClassName
    0.28
    æķĪ
    0.27
    .nb
    0.26
    elts
    0.26
    æİĴéĺŁ
    0.26
     fibers
    0.25
    åħīèį£
    0.24
     fiber
    0.24
     finite
    0.23
    brook
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.