© 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. 41725
    Prev
    Next
    INDEX
    Explanations

    pledged of goal

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    haber
    -0.07
    ä¸įåĥı
    -0.07
    phasis
    -0.07
    _FORCE
    -0.07
    inese
    -0.07
    åħĭç¦ı
    -0.07
    æĭĨ
    -0.06
    oller
    -0.06
    aber
    -0.06
    POSITIVE LOGITS
     pales
    0.08
    两èĢħ
    0.08
    çĥ«
    0.07
    zare
    0.07
    tku
    0.07
    -console
    0.07
    说æĺİ
    0.07
    uhu
    0.06
    缸è¾ħ缸æĪIJ
    0.06
    å±ŀä¸ĭ
    0.06
    Activations Density 0.010%

    No Known Activations