© 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. 21905
    Prev
    Next
    INDEX
    Explanations

    zone, fever, diving, aerospace, military

    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
    è°ĥ
    -0.08
    å¾·åŁº
    -0.07
    調
    -0.07
    å¾·éŁ³
    -0.07
    侧éĿ¢
    -0.07
    éĹ´æİ¥
    -0.07
    crypto
    -0.06
    大åħ³
    -0.06
    æľ¦èĥ§
    -0.06
    iled
    -0.06
    POSITIVE LOGITS
    æĪĸåľ¨
    0.10
     primordial
    0.08
    thur
    0.08
    寮
    0.07
    oroz
    0.07
    åĽ½å®¶è§Ħå®ļ
    0.07
    æĪĸ使çĶ¨
    0.07
    useum
    0.07
    æĪĸä¸İ
    0.07
    landa
    0.07
    Activations Density 0.281%

    No Known Activations