© 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. 61615
    Prev
    Next
    INDEX
    Explanations

    prize, pic, pizza

    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
    ÏĤ
    -0.08
    éĴµ
    -0.07
    ############################################################################
    -0.07
    werk
    -0.07
    çĶļèĩ³æľī
    -0.07
    upos
    -0.07
    óra
    -0.07
    stra
    -0.06
    ijIJ
    -0.06
    ¯¯¯¯
    -0.06
    POSITIVE LOGITS
    र
    0.08
    ¨
    0.07
    大åī§éĻ¢
    0.07
    acker
    0.07
    ftware
    0.07
    ledge
    0.06
    avigator
    0.06
    reiz
    0.06
    .nlm
    0.06
    æ°¸å®ī
    0.06
    Activations Density 0.139%

    No Known Activations