© 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. 16982
    Prev
    Next
    INDEX
    Explanations

    COMMONWEALTH OF PENNSYLVANIA

    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
    elters
    -0.06
    ä¸ĸçļĦ
    -0.05
    å«Į
    -0.05
    åĨįæľī
    -0.05
    odr
    -0.05
    habil
    -0.05
    침
    -0.05
    è¶ħè¿ĩ约
    -0.05
    ضة
    -0.05
    emble
    -0.05
    POSITIVE LOGITS
    arl
    0.06
    rl
    0.06
    alia
    0.06
    æģŃåĸľä½ł
    0.05
    empa
    0.05
    arius
    0.05
    rangle
    0.05
    rus
    0.05
    деÑĤÑģÑı
    0.05
    ife
    0.05
    Activations Density 0.002%

    No Known Activations