© 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. 4372
    Prev
    Next
    INDEX
    Explanations

    as provided, as found, as published, as shown

    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
    iola
    -0.09
    èĽĬ
    -0.09
    שת
    -0.08
    áĥĺáĥĽ
    -0.08
    heds
    -0.08
    Ñīенко
    -0.08
    oncini
    -0.08
    åĪĨç±»åı·
    -0.08
    .library
    -0.08
    çĥŃ线çĶµè¯Ŀ
    -0.08
    POSITIVE LOGITS
    Âł
    0.07
    aser
    0.07
    æĶ
    0.06
    ting
    0.06
     Âł
    0.06
    lo
    0.06
    aky
    0.06
     requirements
    0.05
    azer
    0.05
    æĶ¶è´§
    0.05
    Activations Density 0.007%

    No Known Activations