© 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. 38708
    Prev
    Next
    INDEX
    Explanations

    ranges and separators

    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
    []"
    -0.09
    天ä¸ĭ
    -0.08
    ÑģнÑĭ
    -0.08
    _CIPHER
    -0.08
    -extra
    -0.08
    #ad
    -0.08
    æĸ°ä¹¦
    -0.08
    cpy
    -0.08
    çĴ°
    -0.08
    天ä¸ĭçļĦ
    -0.08
    POSITIVE LOGITS
     except
    0.10
    éĻ¤
    0.09
    éĻ¤å¤ĸ
    0.08
     apart
    0.08
    except
    0.08
    以åıĬåľ¨
    0.08
    以åıĬ
    0.08
    è¦ģä¹Ī
    0.07
    以åıĬä¸ĢäºĽ
    0.07
    éĻ¤æѤ
    0.07
    Activations Density 0.227%

    No Known Activations