© 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. 47851
    Prev
    Next
    INDEX
    Explanations

    pointing

    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
     points
    -0.07
    wig
    -0.07
    rix
    -0.07
    decl
    -0.06
    .exception
    -0.06
    points
    -0.06
    æĶ¾å®½
    -0.06
     exceptions
    -0.06
    aven
    -0.06
     uncovered
    -0.06
    POSITIVE LOGITS
    çºłç¼ł
    0.09
    æĭ´
    0.08
     [âĢ¦
    0.08
    ibble
    0.08
    engk
    0.07
     simul
    0.07
    apé
    0.07
    esper
    0.07
    ibbon
    0.07
    джÑĥ
    0.07
    Activations Density 0.007%

    No Known Activations