© 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. 39533
    Prev
    Next
    INDEX
    Explanations

    URL parameters

    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
    angg
    -0.07
    裳
    -0.07
     opil
    -0.07
    araf
    -0.07
    arez
    -0.06
    foobar
    -0.06
    fol
    -0.06
    atat
    -0.06
    ãĥ¼ãĥĪãĥ«
    -0.06
    artige
    -0.06
    POSITIVE LOGITS
    			 ↵
    0.07
    æݧèĤ¡æľīéĻIJåħ¬åı¸
    0.07
    —I
    0.07
    lfw
    0.07
    rou
    0.06
    affer
    0.06
    çģ«çĥ§
    0.06
    insel
    0.06
    æŀª
    0.06
     наполни
    0.06
    Activations Density 0.045%

    No Known Activations