© 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. 24844
    Prev
    Next
    INDEX
    Explanations

    code block control flow

    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
    ithub
    -0.09
    大å§IJ
    -0.08
    微信åı·
    -0.07
    igg
    -0.07
    BUTTON
    -0.07
    ubl
    -0.07
    chap
    -0.07
    ubar
    -0.07
    refs
    -0.07
    igna
    -0.07
    POSITIVE LOGITS
    }else
    0.12
    #else
    0.10
    #elif
    0.08
    }elseif
    0.07
    }catch
    0.07
    ;break
    0.07
    ;}
    0.07
     whereas
    0.07
    kers
    0.07
    ä¸įå¦Ĥ
    0.06
    Activations Density 0.167%

    No Known Activations