© 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. 15507
    Prev
    Next
    INDEX
    Explanations

    androgen receptor, reductase, vestibular

    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
    istring
    -0.07
    èIJĮ
    -0.06
    æ»
    -0.06
    éĵ¶è¡ĮèĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.06
    æĺ¯ä¸ĢéŨ
    -0.06
    oskop
    -0.06
     nice
    -0.06
    .ne
    -0.06
    åIJ«éĩijéĩı
    -0.06
    ç»ĥ
    -0.06
    POSITIVE LOGITS
    缺失
    0.09
    erci
    0.09
     missing
    0.09
    丧失äºĨ
    0.08
    æĹłæ³ķæŃ£å¸¸
    0.08
    踪影
    0.08
     Missing
    0.08
    _missing
    0.08
    æĹłå¿ĥ
    0.08
    缺
    0.08
    Activations Density 0.331%

    No Known Activations