© 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. 8019
    Prev
    Next
    INDEX
    Explanations

    width, height, cellpadding

    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
    ½ij
    -0.07
    -pdf
    -0.07
    olley
    -0.07
    ä¸Ģè¿ŀ
    -0.07
    ile
    -0.06
    leck
    -0.06
    è¿Ŀæ³ķ
    -0.06
    -thumb
    -0.06
    åłĤåłĤ
    -0.06
     ÑģледÑĥÑİÑīей
    -0.06
    POSITIVE LOGITS
    ebt
    0.08
    mute
    0.08
    IW
    0.07
     Burton
    0.07
    stp
    0.07
    ÑħодÑĥ
    0.07
    æķ²
    0.07
    ModelProperty
    0.06
    nas
    0.06
    pum
    0.06
    Activations Density 0.181%

    No Known Activations