© 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. 16992
    Prev
    Next
    INDEX
    Explanations

    possessive attributes or accompanying features

    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
    éĿłå±±
    -0.06
    หล
    -0.06
    lessly
    -0.06
    ceb
    -0.06
    elve
    -0.06
    .sul
    -0.06
    åĨį以
    -0.06
    ülÅij
    -0.06
    stage
    -0.05
    óst
    -0.05
    POSITIVE LOGITS
    家
    0.05
    ãģ³
    0.05
    ç§ij
    0.05
    æ£Ĵ
    0.05
    ences
    0.05
    计ç®Ĺæľº
    0.05
    dez
    0.05
    çij¾
    0.05
    家常
    0.05
    opportun
    0.05
    Activations Density 0.007%

    No Known Activations