© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65179
    Prev
    Next
    INDEX
    Explanations

    numbers zero and one, ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zal
    -0.07
    ulp
    -0.07
    éĥ½ä»¥
    -0.07
    æĿ¥å¹´
    -0.06
    POCH
    -0.06
    iru
    -0.06
    达产年
    -0.06
    Ĥ¬
    -0.06
    éĥ½åºĶ
    -0.06
    为äºĨ满足
    -0.06
    POSITIVE LOGITS
    æĹ¶è¡¨ç¤º
    0.09
    表示
    0.07
    æĬĢæľ¯çĽijçĿ£
    0.07
    åĪĻ表示
    0.07
    表示èĩªå·±
    0.07
    表æĺİ
    0.07
    idane
    0.07
    issy
    0.07
    pecies
    0.07
    å¤ļæīį
    0.07
    Activations Density 0.014%

    No Known Activations