© 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. 9268
    Prev
    Next
    INDEX
    Explanations

    whole, ordinary, my, certain, various

    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
    adah
    -0.07
    arz
    -0.07
    äch
    -0.06
    zien
    -0.06
    ovah
    -0.06
    åħ¨éĻ¢
    -0.06
     unh
    -0.06
    åħ¨æĿij
    -0.06
    ÑĢик
    -0.06
    åĨį说
    -0.05
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩéĥ½
    0.10
    çĪ±ä¸į
    0.09
    产åĵģåľ¨
    0.09
     Ejem
    0.08
    æĥħåĨµä¸ĭ
    0.08
    ä¿¡æģ¯çĶ±
    0.08
    å®Ŀé¾Ļ
    0.08
    ä¹ĭå¤Ħåľ¨äºİ
    0.08
    人ä¸į
    0.08
    çĤ¹å·¦åı³
    0.08
    Activations Density 0.041%

    No Known Activations