© 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. 45470
    Prev
    Next
    INDEX
    Explanations

    protection, alignment, functioning, use

    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
    icultura
    -0.06
     Korn
    -0.06
    fax
    -0.06
    åħ¼
    -0.06
    è¿ĻèĤ¡
    -0.06
    ÑĪÑĤ
    -0.06
    å¤§ä½ľ
    -0.06
    orus
    -0.06
    afia
    -0.06
    æŀģäºĨ
    -0.06
    POSITIVE LOGITS
    iveness
    0.08
    çĶŁåij½è´¢äº§å®īåħ¨
    0.07
    人åĪ°
    0.07
    çĦ¶å¤§
    0.07
    osci
    0.07
    azz
    0.07
    unj
    0.07
    çĤ¹èĩ³
    0.07
    /values
    0.07
    rières
    0.07
    Activations Density 0.050%

    No Known Activations