© 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. 9381
    Prev
    Next
    INDEX
    Explanations

    Web-related text

    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
    好äºĭ
    -0.29
    oret
    -0.28
    ligt
    -0.27
    hua
    -0.26
    abouts
    -0.25
    sten
    -0.25
    <?↵
    -0.23
    STER
    -0.23
    ä½łè¯´
    -0.23
    ehr
    -0.22
    POSITIVE LOGITS
     here
    1.88
    åľ¨è¿ĻéĩĮ
    1.63
    è¿ĻéĩĮ
    1.63
    here
    1.51
     Here
    1.48
    Here
    1.46
     HERE
    1.37
    è¿ĻéĩĮçļĦ
    1.34
    éĢĻ裡
    1.33
    è¿ĻéĩĮæĺ¯
    1.30
    Activations Density 0.000%

    No Known Activations