© 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. 3773
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    å¹²èĦĨ
    -0.08
    çĻ¾åº¦çĻ¾ç§ij
    -0.07
    anut
    -0.07
    äºİæĺ¯åľ¨
    -0.07
    abilit
    -0.06
    etit
    -0.06
    äºİæĺ¯
    -0.06
    aufs
    -0.06
    åĸĤåħ»
    -0.06
    çĶ
    -0.06
    POSITIVE LOGITS
    isar
    0.08
    è¿ijäºĽ
    0.07
    isArray
    0.07
    身çĤº
    0.07
    oc
    0.07
    rose
    0.07
    åĬ³æĸ¯
    0.07
    å¾·å°Ķ
    0.07
    åİ»åıĤåĬł
    0.07
    æĿ¥åıĤåĬł
    0.07
    Activations Density 0.001%

    No Known Activations