© 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. 3879
    Prev
    Next
    INDEX
    Explanations

    code delimiters and types

    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
     Fol
    -0.06
    é¦
    -0.06
    uet
    -0.06
     atlas
    -0.06
    ee
    -0.06
    A
    -0.06
    tent
    -0.06
    å±±ä¸ľå¤§åѦ
    -0.06
    âĢ
    -0.06
    åįļè§Ī
    -0.05
    POSITIVE LOGITS
    elsey
    0.09
    ids
    0.08
    çĻ½éľ²
    0.08
    éŃģ
    0.08
    èľĺ
    0.08
    iders
    0.08
    éĥ´
    0.08
    ç³Ĭ
    0.08
    æĻ®ç½Ĺ
    0.07
     disso
    0.07
    Activations Density 0.015%

    No Known Activations