© 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. 33579
    Prev
    Next
    INDEX
    Explanations

    evaluation terms

    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
    ä¸Ĭè¿°äºĭå®ŀ
    -0.08
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    代表çĿĢ
    -0.07
    éĥ½åľ¨
    -0.07
    ridge
    -0.06
    第ä¸ĢæŶéĹ´
    -0.06
    conds
    -0.06
    åĪĻåľ¨
    -0.06
    _pickle
    -0.06
    andai
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸į太
    0.08
    æŃ¤é¡¹
    0.08
    éĥ½ä¸į太
    0.08
    ริ
    0.07
    awei
    0.07
    NAL
    0.07
    éric
    0.07
    angen
    0.07
    aver
    0.07
    aken
    0.07
    Activations Density 0.002%

    No Known Activations