© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    We are

    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
    å·´æĭī
    -0.07
    amp
    -0.07
    atto
    -0.07
    lamour
    -0.06
    èĢģåİ»
    -0.06
     aga
    -0.06
    åľ¨è¢«
    -0.06
    NewLabel
    -0.06
    åħ¶å®ĥ
    -0.06
    üsse
    -0.06
    POSITIVE LOGITS
    ä¸Ģä¸ĭåIJ§
    0.08
    versa
    0.08
    éĢīä¸Ģ
    0.07
    èģĬèģĬ
    0.07
    ä¸Ģä¸ĭ
    0.07
    _traffic
    0.07
    nep
    0.07
    å¤ķ
    0.07
    éné
    0.07
    ENDOR
    0.07
    Activations Density 0.002%

    No Known Activations