© 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. 19160
    Prev
    Next
    INDEX
    Explanations

    ability to

    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
    åĬ²
    -0.06
    åĬĽäºī
    -0.06
     accordingly
    -0.06
     its
    -0.05
    Ñħодом
    -0.05
    夫åŃIJ
    -0.05
    tiv
    -0.05
    elik
    -0.05
    isis
    -0.05
    REQ
    -0.05
    POSITIVE LOGITS
     oneself
    0.07
     seguito
    0.05
     воÑģпа
    0.05
    γά
    0.05
    ä½łå¾Ī
    0.05
    вÑıз
    0.05
     disparate
    0.05
     dével
    0.05
     elkaar
    0.05
    agar
    0.05
    Activations Density 0.027%

    No Known Activations