© 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. 46314
    Prev
    Next
    INDEX
    Explanations

    `+` markers and code changes

    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
    atal
    -0.08
    دد
    -0.07
    ipy
    -0.07
    ATAL
    -0.07
    iscos
    -0.07
    enheim
    -0.07
    ظÙĩ
    -0.07
    éĢļè¿ĩçĶµè¯Ŀ
    -0.07
     Stamm
    -0.07
    γγ
    -0.06
    POSITIVE LOGITS
    æ±Ĥ羣åĬ¡å®ŀ
    0.07
    jit
    0.07
    имÑĥ
    0.07
    æݨèįIJéĺħ读
    0.06
    è¡¥çŁŃ
    0.06
     sacked
    0.06
    roll
    0.06
    æĬĬä½łçļĦ
    0.06
    å¾Ĺèµ·
    0.06
    缸åħ³æݨèįIJ
    0.06
    Activations Density 0.028%

    No Known Activations