© 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. 42762
    Prev
    Next
    INDEX
    Explanations

    citation indices

    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
    æ±Ĥç²¾
    -0.07
    idou
    -0.07
    iciel
    -0.07
    çķĻåľ¨
    -0.06
    Invariant
    -0.06
    ols
    -0.06
    æıī
    -0.06
    ×IJ×Ļ
    -0.06
    itore
    -0.06
    æ¸ħè¿ľ
    -0.06
    POSITIVE LOGITS
    apper
    0.08
     upto
    0.08
    thon
    0.07
    Ùıب
    0.07
    åľĭéĺ²
    0.07
    brug
    0.07
     '`
    0.07
     Pune
    0.07
    å
    0.07
    çĶ³æĺİ
    0.07
    Activations Density 0.084%

    No Known Activations