© 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. 28706
    Prev
    Next
    INDEX
    Explanations

    rounded to

    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
     prosp
    -0.07
    apol
    -0.07
    essar
    -0.07
    æŀĹåĩ¡
    -0.07
    ò
    -0.07
    计åĪĨ
    -0.06
    indi
    -0.06
    sov
    -0.06
    ä¾łä¼ł
    -0.06
    å®ĪåĪĻ
    -0.06
    POSITIVE LOGITS
    ç®Ģ称
    0.09
    以ä¸ĭç®Ģ称
    0.08
     Ums
    0.07
    æİł
    0.07
    _dep
    0.07
    uvres
    0.06
    dra
    0.06
    æĪijçŃī
    0.06
    åĵİåijĢ
    0.06
    å§ĭ
    0.06
    Activations Density 0.039%

    No Known Activations