© 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. 28264
    Prev
    Next
    INDEX
    Explanations

    stacked or adjusted stacking

    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
    ahoo
    -0.08
    lew
    -0.08
    .float
    -0.07
    _converter
    -0.07
    éĹŃ
    -0.07
    æµ·è§Ĵ
    -0.07
    arle
    -0.07
    kit
    -0.07
    EntityType
    -0.07
    交
    -0.07
    POSITIVE LOGITS
     taller
    0.09
     tallest
    0.08
    olid
    0.08
    åŃĺåľ¨æĦŁ
    0.08
     height
    0.07
     пÑĢиÑģÑĥÑĤÑģÑĤвие
    0.07
     presence
    0.07
    isEmpty
    0.07
     présence
    0.07
    gid
    0.07
    Activations Density 0.001%

    No Known Activations