© 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. 15934
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    agalan
    -0.10
    hton
    -0.09
    æķ¬è¯·æľŁå¾ħ
    -0.08
    था
    -0.08
    avax
    -0.08
    estern
    -0.08
    alter
    -0.08
    ئÙħ
    -0.08
    isclosed
    -0.08
    asley
    -0.08
    POSITIVE LOGITS
    对åIJĦç§į
    0.07
    ä¸Ĭä¸ĭ
    0.07
     I
    0.06
    ilas
    0.06
    -
    0.06
     qu
    0.06
    ULE
    0.06
     random
    0.06
     suggesting
    0.06
    è§ĦåĪĻåĴĮ
    0.05
    Activations Density 0.000%

    No Known Activations