© 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. 64837
    Prev
    Next
    INDEX
    Explanations

    timeout or hangs

    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
     comp
    -0.07
    RIEND
    -0.06
    份
    -0.06
    éĥijéĩį声æĺİ
    -0.06
     parap
    -0.06
    æĹ¢èĥ½
    -0.06
    erlo
    -0.06
    è¦ģä¹Ī
    -0.06
     theirs
    -0.06
    SKIP
    -0.06
    POSITIVE LOGITS
    åı¯èĥ½æĺ¯åĽłä¸º
    0.10
    phem
    0.08
    vens
    0.08
    pcs
    0.07
    æİĮä¸Ĭ
    0.07
    æľªåıĬæŶ
    0.07
    ardown
    0.07
    æį·
    0.07
    æĭ¿æįı
    0.07
    agam
    0.07
    Activations Density 0.002%

    No Known Activations