© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14996
    Prev
    Next
    INDEX
    Explanations

    looping on integers or counters

    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
    强弱
    -0.07
    پذ
    -0.07
    ä¸Ńå¾ĹåĪ°
    -0.07
    çĻ½çŁ³
    -0.06
    etics
    -0.06
    essions
    -0.06
    ä¸į以
    -0.06
    æĺķ
    -0.06
    ç¿ĺ
    -0.06
    lator
    -0.06
    POSITIVE LOGITS
    第ä¸ī次
    0.09
    åĪĿå§ĭ
    0.08
    èįĢ
    0.08
    _INTEGER
    0.08
    otime
    0.07
     incremented
    0.07
    lemn
    0.07
    unos
    0.07
    èµ·å§ĭ
    0.07
     increments
    0.07
    Activations Density 0.004%

    No Known Activations