© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44790
    Prev
    Next
    INDEX
    Explanations

    disjoint, orthogonal, non-overlapping

    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
    illard
    -0.10
    imba
    -0.09
    akwa
    -0.08
    åıĬéħį件
    -0.08
    erja
    -0.08
    äºĨä¸Ģç§į
    -0.08
    coni
    -0.08
    å¦ĤèĬ±
    -0.07
    ceptor
    -0.07
    éĥ¨å°±
    -0.07
    POSITIVE LOGITS
    ness
    0.13
    ed
    0.10
    aneous
    0.09
    à¥į
    0.09
    ingly
    0.09
    ly
    0.08
    anee
    0.08
     nhau
    0.08
    esse
    0.07
    aneously
    0.07
    Activations Density 0.003%

    No Known Activations