© 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. 11544
    Prev
    Next
    INDEX
    Explanations

    a person or thing performing an action

    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
     Finger
    -0.08
    æķ²éŨ
    -0.07
    åĽłä¸ºå®ĥ们
    -0.07
     crumbling
    -0.07
     scratch
    -0.07
     ticking
    -0.07
    cratch
    -0.07
    ạnh
    -0.07
    è½°è½°
    -0.07
    iedade
    -0.07
    POSITIVE LOGITS
    人ä½ĵ
    0.09
     brevet
    0.08
    ä¸įæħİ
    0.07
    éĿĻæŃ¢
    0.07
    who
    0.07
    è¶ħéĩį
    0.07
    ä½ĵéĩį
    0.07
    éŃģ
    0.07
     stationary
    0.07
    æ©
    0.07
    Activations Density 0.029%

    No Known Activations