© 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. 47404
    Prev
    Next
    INDEX
    Explanations

    right-hand

    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
    masked
    -0.07
    vec
    -0.07
     distinctions
    -0.07
    mask
    -0.06
    .ZERO
    -0.06
    pickle
    -0.06
    zyw
    -0.06
    scr
    -0.06
    etet
    -0.06
    éģ®çĽĸ
    -0.06
    POSITIVE LOGITS
    ondo
    0.07
    rouch
    0.07
    è±ģ
    0.07
    .exports
    0.07
    èħĨ
    0.07
    .opend
    0.07
    asmus
    0.07
    +C
    0.06
    è«
    0.06
    itchens
    0.06
    Activations Density 0.049%

    No Known Activations