© 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. 33324
    Prev
    Next
    INDEX
    Explanations

    "for all"

    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
    æīĢæľīè¿ĻäºĽ
    -0.08
    icka
    -0.07
    çļĦä¸ĢåĪĩéĥ½
    -0.07
    ä¸Ģ个ä¸Ģ个
    -0.06
    elpers
    -0.06
    riel
    -0.06
    ruÄį
    -0.06
     itself
    -0.06
    两åѦä¸Ģåģļ
    -0.06
    åħ¨ä½ĵåijĺå·¥
    -0.06
    POSITIVE LOGITS
     except
    0.10
     Except
    0.09
    except
    0.08
    Except
    0.08
    μοÏįÏĤ
    0.08
    igner
    0.08
    unas
    0.07
     sauf
    0.07
    decltype
    0.07
    姬
    0.07
    Activations Density 0.006%

    No Known Activations