© 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. 33442
    Prev
    Next
    INDEX
    Explanations

    whether, understanding, which, download

    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
    uyan
    -0.07
    å·§
    -0.06
    odd
    -0.06
    çīµ
    -0.06
    ÙĪد
    -0.06
    -0.06
    èĩªæĪij
    -0.06
    壮大
    -0.06
    ç§Ģ
    -0.06
     Tra
    -0.06
    POSITIVE LOGITS
    allee
    0.09
    Configs
    0.09
    geno
    0.08
    åĩĨåŃĹ
    0.08
    .units
    0.08
    bery
    0.08
    accord
    0.08
    ÑĥÑĢе
    0.08
    erde
    0.08
    Units
    0.08
    Activations Density 0.005%

    No Known Activations