© 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. 29659
    Prev
    Next
    INDEX
    Explanations

    you think

    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
    çĴ
    -0.07
    çŁ¾
    -0.07
    krim
    -0.07
     vess
    -0.07
    磶
    -0.07
    æ²ĥæĸ¯
    -0.07
    æ¼
    -0.06
    æĺĨ
    -0.06
    ê±°
    -0.06
    udes
    -0.06
    POSITIVE LOGITS
    åħ¨æĸĩéĺħ读
    0.07
    andong
    0.07
    éĢıæĶ¯
    0.07
    ÑıÑĤÑģÑı
    0.07
    人çĤº
    0.06
    çĿĽ
    0.06
    <tool_response>
    0.06
    ynamo
    0.06
    avais
    0.06
    modifiable
    0.06
    Activations Density 0.004%

    No Known Activations