© 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. 28551
    Prev
    Next
    INDEX
    Explanations

    brief explanation or discussion

    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
    çŃīå¤ļç§į
    -0.07
     precisely
    -0.06
    以åıĬåIJĦç§į
    -0.06
    erus
    -0.06
    ä»Ķç»Ĩåľ°
    -0.06
    eberg
    -0.06
     meticulously
    -0.06
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.06
    eku
    -0.06
    ngr
    -0.06
    POSITIVE LOGITS
    ç®Ģè¦ģ
    0.09
    åį³åı¯
    0.09
    åĩłæĿ¡
    0.09
    ëĤĺë§Ī
    0.09
    äºĨ解ä¸Ģä¸ĭ
    0.09
     gá»įn
    0.08
    äºĨ解ä¸ĭ
    0.08
    åIJİåį³åı¯
    0.08
    ëĿ¼ëıĦ
    0.08
    /simple
    0.08
    Activations Density 0.100%

    No Known Activations