© 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. 45887
    Prev
    Next
    INDEX
    Explanations

    key pairs

    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
    omen
    -0.06
    ifero
    -0.06
    osa
    -0.06
    ãģ«åħ¥ãĤĮãĤĭ
    -0.06
    put
    -0.06
    为åħĪ
    -0.06
     ÑĥпоÑĤÑĢеблÑı
    -0.06
    orum
    -0.06
    LOWER
    -0.06
    ll
    -0.06
    POSITIVE LOGITS
    Cancellation
    0.09
    åĪĨå¼Ģ
    0.08
    åĽ¢æĪIJåijĺ
    0.08
     pair
    0.08
    æľīåģ¿
    0.08
     pairs
    0.07
    缸çĪ±
    0.07
    éħį对
    0.07
    renc
    0.07
    æ´Ľå¤«
    0.07
    Activations Density 0.014%

    No Known Activations