© 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. 13653
    Prev
    Next
    INDEX
    Explanations

    iterations, divisions, length

    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
    andalone
    -0.08
     sẵn
    -0.08
    åįĥéĩij
    -0.08
    åįĥ人
    -0.08
    asso
    -0.08
    cope
    -0.07
    Scope
    -0.07
    porté
    -0.07
    zyw
    -0.07
    igram
    -0.07
    POSITIVE LOGITS
    åĩłæ¬¡
    0.09
     successive
    0.09
     iterations
    0.08
    iterations
    0.08
    è¿Ń代
    0.08
    æķ°æ¬¡
    0.08
    ä½įæķ°
    0.07
     cycles
    0.07
     divisions
    0.07
    次æķ°
    0.07
    Activations Density 0.004%

    No Known Activations