© 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. 57097
    Prev
    Next
    INDEX
    Explanations

    site, location

    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
     contents
    -0.28
    itary
    -0.28
    ugi
    -0.27
    -main
    -0.26
    è¿Ľé©»
    -0.26
    åħ«åį¦
    -0.26
    olv
    -0.25
    insic
    -0.25
    æĸĩåĮĸä¼łæĴŃ
    -0.24
    åĿIJèIJ½
    -0.24
    POSITIVE LOGITS
     where
    0.43
    where
    0.40
    WHERE
    0.36
    Where
    0.36
     Where
    0.36
    	where
    0.29
     WHERE
    0.29
     где
    0.28
    _where
    0.28
     wherein
    0.27
    Activations Density 0.006%

    No Known Activations