© 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. 9112
    Prev
    Next
    INDEX
    Explanations

    password reset

    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
    renc
    -0.07
     cev
    -0.07
    _mtime
    -0.07
    CEE
    -0.07
    RIA
    -0.07
    è¿Ļ个çĶ·äºº
    -0.07
    ynt
    -0.07
    repid
    -0.07
    APT
    -0.07
    åīį段æŶéĹ´
    -0.07
    POSITIVE LOGITS
    ilu
    0.07
     Ùħخت
    0.07
    èĩªçĶ±
    0.06
    ìĬ¬
    0.06
    oglio
    0.06
    ugin
    0.06
    pis
    0.06
    fffffff
    0.06
     complimentary
    0.06
    ä¸Ģå¤ķ
    0.06
    Activations Density 0.001%

    No Known Activations