© 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. 32940
    Prev
    Next
    INDEX
    Explanations

    degree, index, dimensional, length, rank

    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
    [:-
    -0.08
    æĹłçĥŁ
    -0.07
     Khang
    -0.07
    uari
    -0.07
    ease
    -0.07
    éĢĤéĩı
    -0.06
    æĺ¥ç¬ĭ
    -0.06
    æºĢè¼ī
    -0.06
    boro
    -0.06
    használ
    -0.06
    POSITIVE LOGITS
    è·ĭæ¶ī
    0.08
    ì§ľ
    0.07
    æĽ²æĬĺ
    0.07
    éķ¿åľ¨
    0.07
    /native
    0.07
     exotic
    0.07
    _OC
    0.07
    native
    0.07
    缮ä¸Ń
    0.07
     kac
    0.07
    Activations Density 0.004%

    No Known Activations