© 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. 56678
    Prev
    Next
    INDEX
    Explanations

    speedy past thread

    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
    è´µåħ¬åı¸
    -0.07
    θοÏĤ
    -0.07
     Hold
    -0.07
    ãģ·
    -0.07
    èĢķèĢĺ
    -0.07
    oces
    -0.06
    olon
    -0.06
     observations
    -0.06
    èĩªè§īéģµå®Ī
    -0.06
    éĥijéĩį声æĺİ
    -0.06
    POSITIVE LOGITS
    çĶ¨æŶ
    0.06
    _SA
    0.06
     dad
    0.06
    eden
    0.06
    deal
    0.06
    è°Ń
    0.06
    çĭ¼
    0.06
     faults
    0.06
    lict
    0.06
    accio
    0.06
    Activations Density 0.163%

    No Known Activations