© 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. 27150
    Prev
    Next
    INDEX
    Explanations

    effect of

    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
     it
    -0.06
    quin
    -0.06
    ilty
    -0.06
    äºĪ以
    -0.06
    empre
    -0.06
    rape
    -0.06
    éĢĤçĶ¨
    -0.06
    å±ĢéĿ¢
    -0.06
    æĸ¤
    -0.05
    çĶ±
    -0.05
    POSITIVE LOGITS
    çŃīåĽłç´ł
    0.10
    ä¸Ģç»ıåıijçİ°
    0.08
    çİ°å°Ĩ
    0.08
    åľ¨æŃ¤æ¬¡
    0.08
     versus
    0.08
    èĢĮèµ·
    0.08
    à¸Ĥัà¸Ļ
    0.08
    agog
    0.08
    IBUT
    0.07
    bots
    0.07
    Activations Density 0.403%

    No Known Activations