© 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. 17235
    Prev
    Next
    INDEX
    Explanations

    found/thought/idea followed by solution/answer

    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
    .bz
    -0.08
    çļĦéĥ½æĺ¯
    -0.08
    akta
    -0.08
    ajer
    -0.07
    讳
    -0.07
    å°½
    -0.07
    ulich
    -0.07
    è¾ľè´Ł
    -0.07
    iber
    -0.07
    åĬĽåĽ¾
    -0.07
    POSITIVE LOGITS
    æĥ³åĪ°
    0.08
    æĥ³åĪ°äºĨ
    0.08
    !
    0.07
    !--
    0.07
    并ç»ı
    0.07
     enfin
    0.07
    æľīäºĨ
    0.07
    !:
    0.07
    !.
    0.07
    !!!
    0.07
    Activations Density 0.046%

    No Known Activations