© 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. 49603
    Prev
    Next
    INDEX
    Explanations

    sequence of zeros

    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
    hol
    -0.08
    js
    -0.06
     zer
    -0.06
    har
    -0.06
    ç§ģä¸ĭ
    -0.06
    ahoo
    -0.06
     individually
    -0.06
     Harness
    -0.06
     паÑĢÑĤ
    -0.06
    /reference
    -0.06
    POSITIVE LOGITS
    odik
    0.09
    ubbo
    0.09
    nern
    0.09
    otypical
    0.08
    æºī
    0.08
    ÙĤاÙĨ
    0.08
    olumn
    0.08
    ijek
    0.07
    utel
    0.07
    mato
    0.07
    Activations Density 0.008%

    No Known Activations