© 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. 19154
    Prev
    Next
    INDEX
    Explanations

    Marshall recent

    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
    èĪŁ
    -0.08
    ance
    -0.08
    auta
    -0.08
    cosa
    -0.08
    goed
    -0.08
    itionally
    -0.08
    뢰
    -0.08
    lick
    -0.08
    ffer
    -0.08
    æľ¬åºĹ
    -0.08
    POSITIVE LOGITS
     Ep
    0.06
    ems
    0.06
     ep
    0.06
     happen
    0.06
    ok
    0.06
    oley
    0.06
    å¦Ĥæŀľä½łå¯¹
    0.06
    æķħåIJį
    0.06
     frm
    0.06
    istem
    0.06
    Activations Density 0.008%

    No Known Activations