© 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. 45808
    Prev
    Next
    INDEX
    Explanations

    abstract description summary reason

    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
    veau
    -0.08
    à¹Ģสà¸Ļ
    -0.08
    Animating
    -0.08
    adden
    -0.07
    aine
    -0.07
    ä¾Ľæ°Ķ
    -0.07
    guas
    -0.07
    onne
    -0.07
    çĻ¾è®¡
    -0.07
    encer
    -0.07
    POSITIVE LOGITS
    hdl
    0.07
     punches
    0.06
    ç®Ģæĺİ
    0.06
    äºļè¿IJ
    0.06
    å¯¹æľ¬æ¬¡
    0.06
    ondre
    0.06
    è¿Ļå¼ł
    0.06
    gang
    0.06
    çŀŃ
    0.06
    har
    0.06
    Activations Density 0.001%

    No Known Activations