© 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. 60345
    Prev
    Next
    INDEX
    Explanations

    share freely

    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
    chy
    -0.09
    Referensi
    -0.09
    icians
    -0.09
    ablish
    -0.09
    essant
    -0.09
    หมาย
    -0.09
    alisierung
    -0.09
    åĬłæĭ¿å¤§
    -0.09
    å¸ĪçļĦ
    -0.08
    สà¹Į
    -0.08
    POSITIVE LOGITS
    edly
    0.10
    able
    0.09
    akespeare
    0.08
    åħ±æ²»
    0.07
    åħ±çĶ¨
    0.07
     باÙĦÙĦÙĩ
    0.07
    м
    0.07
    abouts
    0.06
    h
    0.06
    holding
    0.06
    Activations Density 0.067%

    No Known Activations