© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60088
    Prev
    Next
    INDEX
    Explanations

    calculate the or the

    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
     SAME
    -0.08
    ł
    -0.07
    éķ¿åĪ¶
    -0.07
    说æĺ¯
    -0.07
    gara
    -0.07
     Gabin
    -0.07
     importantly
    -0.07
     mesma
    -0.07
    ¹
    -0.07
     misma
    -0.07
    POSITIVE LOGITS
     value
    0.09
     contribution
    0.08
    IndexOf
    0.08
     effett
    0.08
     chances
    0.07
     approximate
    0.07
     correct
    0.07
     minimum
    0.07
    eneur
    0.07
    åĩºå¤Ħ
    0.07
    Activations Density 0.172%

    No Known Activations