© 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. 45490
    Prev
    Next
    INDEX
    Explanations

    sun bear

    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
    oire
    -0.11
    帼
    -0.10
    echos
    -0.09
    å¦Ĥå±±
    -0.09
    _TODO
    -0.09
    ttp
    -0.08
    uforia
    -0.08
    æĿİè½»
    -0.08
    Õ¸ÖĤÕ©ÕµÕ¸ÖĤÕ¶
    -0.08
    åľŁèĢ³
    -0.08
    POSITIVE LOGITS
    nier
    0.10
    light
    0.09
    åħ¬åħ¬
    0.09
    缴å°Ħ
    0.08
    -facing
    0.07
    -derived
    0.07
    æĻ´
    0.07
    伯伯
    0.07
     Microsystems
    0.07
    ifer
    0.07
    Activations Density 0.030%

    No Known Activations