© 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. 33298
    Prev
    Next
    INDEX
    Explanations

    section or depart

    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
    ‘
    -0.08
     ‘
    -0.07
    æĪĪ
    -0.07
    gow
    -0.06
    rama
    -0.06
    ä¸į失
    -0.06
     subl
    -0.06
    orst
    -0.06
    Gap
    -0.06
    åĦ¿
    -0.06
    POSITIVE LOGITS
    oure
    0.08
    zzle
    0.08
    enus
    0.08
    á»ĩp
    0.07
    á»ħn
    0.07
     Valenci
    0.07
    zza
    0.07
     миÑĢо
    0.07
     coursework
    0.07
    åħ¶èº«
    0.07
    Activations Density 0.017%

    No Known Activations