© 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. 55367
    Prev
    Next
    INDEX
    Explanations

    .then after ç

    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
    ernal
    -0.09
    çĴŀ
    -0.08
    ----</
    -0.08
    InvalidArgumentException
    -0.08
    ÑĢаÑĤно
    -0.08
    juh
    -0.08
    <quote
    -0.08
    vel
    -0.08
    ---</
    -0.08
    ----------</
    -0.08
    POSITIVE LOGITS
    unk
    0.06
    UNK
    0.06
    UC
    0.06
    rq
    0.06
    å©ķ
    0.06
     اÙĦÙħÙģ
    0.06
    泪æµģ
    0.06
    oko
    0.06
    ude
    0.06
    _delegate
    0.06
    Activations Density 0.008%

    No Known Activations