© 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. 42841
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    edan
    -0.08
    ÑĢода
    -0.08
    Äĵj
    -0.08
    подоб
    -0.08
    èĩªçĦ¶èĢĮ
    -0.08
     Merke
    -0.08
    xfan
    -0.08
    lai
    -0.08
    RC
    -0.08
    á»ij
    -0.07
    POSITIVE LOGITS
    å°±åľ¨äºİ
    0.10
     difference
    0.10
    åľ¨äºİ
    0.09
    difference
    0.08
    çĽ¸å·®
    0.08
    åıªå·®
    0.08
    ãģ®éģķãģĦ
    0.07
    å·®äºĨ
    0.07
     differences
    0.07
    Difference
    0.07
    Activations Density 0.016%

    No Known Activations