© 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. 20140
    Prev
    Next
    INDEX
    Explanations

    stand-alone basis

    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
    elep
    -0.07
    åľŁåľ°ä¸Ĭ
    -0.07
    xis
    -0.07
    onha
    -0.07
    éĩijæ¡¥
    -0.07
    ryp
    -0.07
    ìĺģ
    -0.06
    terek
    -0.06
    大路
    -0.06
    onia
    -0.06
    POSITIVE LOGITS
     Caldwell
    0.08
    erst
    0.07
    媲
    0.07
    оÑģÑĮ
    0.07
    çĽı
    0.07
    äºĶ常
    0.07
    à¹Ģà¸Ńาà¹Ħวà¹ī
    0.06
    ä¹±
    0.06
    erno
    0.06
    åľ¨è¿ĻéĩĮ
    0.06
    Activations Density 0.001%

    No Known Activations