© 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. 23678
    Prev
    Next
    INDEX
    Explanations

    DOI and citation numbers

    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
     cali
    -0.08
    أس
    -0.07
    çģŃ
    -0.07
    çĿĢä¸Ģ
    -0.07
    оÑī
    -0.07
    ÃĶI
    -0.07
    ÃģP
    -0.07
    cratch
    -0.06
    ÐŁÐĺ
    -0.06
    ÃĤY
    -0.06
    POSITIVE LOGITS
    æ³ĵ
    0.08
    mir
    0.08
    æĪijåIJ§
    0.08
    สา
    0.07
    dor
    0.06
    rians
    0.06
    Äĵr
    0.06
    inar
    0.06
    åĬłæĭ¿å¤§
    0.06
    aksin
    0.06
    Activations Density 0.006%

    No Known Activations