© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11733
    Prev
    Next
    INDEX
    Explanations

    suspect evidence clues

    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
    師
    -0.07
     bep
    -0.07
    _accessor
    -0.07
     undermin
    -0.07
    ongan
    -0.07
    gnore
    -0.07
    æ³ī
    -0.06
    éģ¿åħįåĽł
    -0.06
    æ²»çIJĨ
    -0.06
     representative
    -0.06
    POSITIVE LOGITS
    线索
    0.13
    å«Įçĸij
    0.12
     suspect
    0.11
    æ¡Īåıij
    0.11
    ä½ľæ¡Ī
    0.11
     corrobor
    0.11
     suspicious
    0.10
    åı¯çĸij
    0.10
     подозÑĢе
    0.10
     clues
    0.10
    Activations Density 0.214%

    No Known Activations