© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17902
    Prev
    Next
    INDEX
    Explanations

    psych psychogenic cognitive ability personality

    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
    usat
    -0.07
     kẹt
    -0.07
    klink
    -0.07
    ajem
    -0.07
     conta
    -0.07
    è½´è·Ŀ
    -0.07
    á»Ļn
    -0.07
     ‘’
    -0.07
    quisite
    -0.07
     Conta
    -0.06
    POSITIVE LOGITS
    ong
    0.06
     mar
    0.05
     times
    0.05
    loe
    0.05
    ri
    0.05
    os
    0.05
    l
    0.05
    ee
    0.05
     Nordic
    0.04
     ter
    0.04
    Activations Density 0.005%

    No Known Activations