© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163024
    Prev
    Next
    INDEX
    Explanations

    [[

    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
    ä¸ĭæĿ¥
    -0.29
    sr
    -0.26
    çŃĸ
    -0.26
    uter
    -0.25
     cân
    -0.25
    (sr
    -0.25
    AndView
    -0.24
    ation
    -0.24
    agedList
    -0.24
    çĨ¨
    -0.24
    POSITIVE LOGITS
    -worker
    0.25
    ogany
    0.24
    ä¸ĢåĽ¢
    0.24
     Dagger
    0.24
    èĿī
    0.23
    noch
    0.23
    omics
    0.23
    unlikely
    0.23
    }?
    0.23
    æŀľçĦ¶
    0.23
    Activations Density 0.168%

    No Known Activations