© 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. 60937
    Prev
    Next
    INDEX
    Explanations

    acetic acid, vessel, month old

    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
     Szk
    -0.08
    agn
    -0.08
    å°
    -0.07
    sein
    -0.07
     miscellaneous
    -0.07
    czyn
    -0.07
     Nog
    -0.07
    æŀ«
    -0.07
    aktur
    -0.07
    综åIJĪçĹĩ
    -0.07
    POSITIVE LOGITS
    å±ŀäºİ
    0.07
    èĵ¦çĦ¶
    0.07
    æĹ¶ä»£çļĦ
    0.07
    ippo
    0.07
    èĻķçļĦ
    0.07
    大夫
    0.07
    æ²ĥæĸ¯
    0.07
    mouseover
    0.06
    поÑĢÑĤа
    0.06
    spar
    0.06
    Activations Density 1.062%

    No Known Activations