© 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. 33327
    Prev
    Next
    INDEX
    Explanations

    did not, let's, is only

    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
    æĦıè§ģ书
    -0.09
    Ĺ
    -0.08
    å¤Ħåľ¨
    -0.08
    ÃīR
    -0.08
     space
    -0.08
    æĻºèĥ½ç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.07
    è¡Ķ
    -0.07
    theid
    -0.07
    Õ¹
    -0.07
     Ponti
    -0.07
    POSITIVE LOGITS
    åħĭ
    0.07
    èĩªçĦ¶æĺ¯
    0.06
     Viz
    0.06
    å½¢
    0.06
    alone
    0.06
    ocal
    0.06
    æĪĺ
    0.06
     alone
    0.06
     god
    0.06
    è¿Ļéĥ¨åĪĨ
    0.06
    Activations Density 0.015%

    No Known Activations