© 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. 46292
    Prev
    Next
    INDEX
    Explanations

    magnetic properties or reversal

    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
    pect
    -0.07
    çģµæ°Ķ
    -0.07
    asar
    -0.06
    çļĻ
    -0.06
    åĸľæ¬¢ä¸Ĭ
    -0.06
     Countdown
    -0.06
    æµģéĩı
    -0.06
     admit
    -0.06
    ponde
    -0.06
    ä¸į误
    -0.06
    POSITIVE LOGITS
    æ°¸ç£ģ
    0.09
    Permanent
    0.09
    tsky
    0.09
    ìŀĶ
    0.08
     hardness
    0.08
     resistance
    0.08
    å·¨
    0.08
    nown
    0.08
    udas
    0.08
    Resistance
    0.08
    Activations Density 0.019%

    No Known Activations