© 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. 55385
    Prev
    Next
    INDEX
    Explanations

    fraction, prime, ivalency, card

    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
    baugh
    -0.09
    ä¸Ģ缴éĥ½åľ¨
    -0.08
    ewe
    -0.08
    ÑĢÑİ
    -0.07
    ienes
    -0.07
    çIJĨäºĭ
    -0.07
     regret
    -0.07
     cumul
    -0.07
     Woodward
    -0.07
    embe
    -0.07
    POSITIVE LOGITS
    åħ¬åĪĨ
    0.07
    ä¸įäºĮ
    0.07
    çĶŁæ´»çļĦ
    0.07
    å¹³çĶŁ
    0.06
    æ¸ħæ¥ļçļĦ
    0.06
    åĩŃ
    0.06
    ׼×ķף
    0.06
    éĵħ
    0.06
    ä¸Ńåħ¬
    0.06
    åħ¬åħ±
    0.06
    Activations Density 0.002%

    No Known Activations