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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8952
    Prev
    Next
    INDEX
    Explanations

    most

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     often
    -0.33
     rarely
    -0.32
    atively
    -0.30
    ably
    -0.30
    lessly
    -0.29
    likely
    -0.29
    ly
    -0.29
     frequently
    -0.29
    istically
    -0.28
    å¾Ģå¾Ģ
    -0.28
    POSITIVE LOGITS
    åħ¨éĥ¨
    0.33
    çļĦæīĢæľī
    0.32
     toute
    0.31
    ä»»ä½ķ
    0.31
     anything
    0.30
    ç»Ŀ大éĥ¨åĪĨ
    0.30
     any
    0.29
    çļĦä¸ĢåĪĩ
    0.29
    ä»»ä½ķ人
    0.29
    åħ¨ãģ¦
    0.29
    Activations Density 0.006%

    No Known Activations