© 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. 163313
    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
     userRepository
    -0.29
    زار
    -0.28
     allot
    -0.28
    ibox
    -0.26
    abox
    -0.26
    responseData
    -0.25
    ibase
    -0.25
    åħħ
    -0.25
    æĹ¥ãģ«
    -0.24
    SCALE
    -0.23
    POSITIVE LOGITS
     Akt
    0.26
     ter
    0.24
    ä¸įé«ĺ
    0.24
    CG
    0.24
     episode
    0.24
    åħ¨éĿ¢
    0.23
     apost
    0.23
    äºĴèģĶäºĴéĢļ
    0.23
    orman
    0.23
    转
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.