© 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. 49046
    Prev
    Next
    INDEX
    Explanations

    overlapping subsets or groups

    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
    born
    -0.07
     quotient
    -0.06
     born
    -0.06
    #/
    -0.06
    astre
    -0.06
     Scalar
    -0.06
    ibar
    -0.06
    lider
    -0.06
     Dank
    -0.06
    åİŁåľ°
    -0.06
    POSITIVE LOGITS
     overlaps
    0.09
     memberships
    0.09
    -members
    0.09
    Overlap
    0.09
     overlapping
    0.09
     intersect
    0.09
     overlap
    0.08
    .intersection
    0.08
    交éĽĨ
    0.08
    overlap
    0.08
    Activations Density 0.017%

    No Known Activations