© 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. 44945
    Prev
    Next
    INDEX
    Explanations

    analyzing and evaluating scenarios

    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
    Ī¬
    -0.08
    红河
    -0.07
    æľīäºĽåľ°æĸ¹
    -0.07
    _detect
    -0.06
    _struct
    -0.06
    åĿł
    -0.06
    ãģ³
    -0.06
    Struct
    -0.06
     Detect
    -0.06
    Detect
    -0.06
    POSITIVE LOGITS
    vary
    0.11
     hypothetical
    0.10
    æĶ¹åıĺ
    0.09
     variations
    0.09
     incremental
    0.09
    ensitivity
    0.09
     scenarios
    0.09
    æķıæĦŁæĢ§
    0.09
    enarios
    0.09
     sensitivity
    0.09
    Activations Density 0.373%

    No Known Activations