© 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. 51637
    Prev
    Next
    INDEX
    Explanations

    alpha-L, neutral prote, N quad, referred to

    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
    _holder
    -0.08
    infeld
    -0.08
    大æĬĬ
    -0.08
    ugat
    -0.07
     Trot
    -0.07
    æ¢ħæŀĹ
    -0.07
    Extensions
    -0.07
     sema
    -0.07
     tÃłng
    -0.07
    kis
    -0.07
    POSITIVE LOGITS
    è½°
    0.09
     missing
    0.09
    è§Ī
    0.08
    æ¯įåŃIJ
    0.08
    缺失
    0.08
    veri
    0.07
     (?,
    0.07
    acol
    0.07
    erie
    0.07
     bombard
    0.07
    Activations Density 0.002%

    No Known Activations