© 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. 41672
    Prev
    Next
    INDEX
    Explanations

    associated with effect or importance

    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
    hofer
    -0.07
    견
    -0.07
    jala
    -0.07
    ç§ĭé£İ
    -0.06
    å¨ĺ
    -0.06
    æµ·æ¶Ľ
    -0.06
    ographies
    -0.06
    åħĪæĿ¥
    -0.06
    æ½¢
    -0.06
    大çģ«
    -0.06
    POSITIVE LOGITS
    idl
    0.09
     consequential
    0.08
    indel
    0.08
    缴æİ¥åħ³ç³»åĪ°
    0.08
    åı¯çĶ¨äºİ
    0.08
    omis
    0.08
    导èĩ´äºĨ
    0.08
    åħ³ä¹İ
    0.08
    åħ³ç³»åĪ°
    0.08
    subst
    0.08
    Activations Density 0.272%

    No Known Activations