© 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. 21581
    Prev
    Next
    INDEX
    Explanations

    questions asking "how" or "where"

    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
    urette
    -0.06
    unders
    -0.06
     Freedom
    -0.05
    iedz
    -0.05
    entifier
    -0.05
    restrict
    -0.05
    гÑĢада
    -0.05
    ç½Ĺæĭī
    -0.05
    å¨ľ
    -0.05
    碰åĪ°
    -0.05
    POSITIVE LOGITS
    eload
    0.05
    àªı
    0.05
    iless
    0.05
    æľīè´£
    0.05
    yle
    0.05
    çŁ¥éĿĴ
    0.05
    orld
    0.05
    addin
    0.05
    á
    0.05
    еÑĢед
    0.05
    Activations Density 0.001%

    No Known Activations