© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18868
    Prev
    Next
    INDEX
    Explanations

    sphere and spherical shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onstruk
    -0.07
    redient
    -0.07
    eger
    -0.07
    еÑģÑĤв
    -0.07
    alap
    -0.07
    ments
    -0.07
    usch
    -0.07
    ãĤī
    -0.07
    oração
    -0.07
    auan
    -0.07
    POSITIVE LOGITS
    仪
    0.06
    à¯ģà®ķ
    0.06
    ighted
    0.06
    pher
    0.05
    enic
    0.05
    ä¹İ
    0.05
    赤éģĵ
    0.05
    еди
    0.05
    curring
    0.05
    gie
    0.05
    Activations Density 0.010%

    No Known Activations