© 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. 38946
    Prev
    Next
    INDEX
    Explanations

    cause, probability, assurance, justification

    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
    aray
    -0.09
    ISTRA
    -0.08
    ekat
    -0.08
     Strateg
    -0.08
    éĢģä¸Ĭ
    -0.08
    anny
    -0.08
    _san
    -0.08
     Biar
    -0.08
    -Ta
    -0.08
    amani
    -0.08
    POSITIVE LOGITS
    ä¸Ķ
    0.07
     enough
    0.07
    æīįè¡Į
    0.07
     vague
    0.07
     criterion
    0.07
     ÑģоÑĢ
    0.06
    åĤį
    0.06
     im
    0.06
    å¤Ł
    0.06
     likely
    0.06
    Activations Density 0.052%

    No Known Activations