© 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. 28255
    Prev
    Next
    INDEX
    Explanations

    90% of

    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
    kort
    -0.10
    kens
    -0.08
    该åIJį
    -0.08
    æľĢåīį沿
    -0.08
    stech
    -0.08
    .Attach
    -0.08
    uhu
    -0.08
    umenta
    -0.08
    rlen
    -0.07
    æĤ¨çļĦéĹ®é¢ĺ
    -0.07
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.09
    ç»Ŀ大éĥ¨åĪĨ
    0.08
     (>
    0.08
    大éĥ¨åĪĨ
    0.08
     except
    0.08
    ãģ¨è¨Ģãģ£ãģ¦
    0.07
    éĥ½æĺ¯çĶ¨
    0.07
     majority
    0.07
    except
    0.07
    éĴŁæĥħ
    0.07
    Activations Density 0.174%

    No Known Activations