© 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. 18563
    Prev
    Next
    INDEX
    Explanations

    database schema names

    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
    ains
    -0.05
    ÏģÏī
    -0.05
    ä¸Ģéĥ¨åĪĨ
    -0.05
    ux
    -0.05
    avn
    -0.05
    idel
    -0.05
    hip
    -0.05
    .stem
    -0.04
    æįŁçĽĬ
    -0.04
    gal
    -0.04
    POSITIVE LOGITS
    ç³»ç»Łè¿Ľè¡Į
    0.06
     طبÛĮعÛĮ
    0.06
    itial
    0.06
    odge
    0.06
    ÅĤud
    0.06
    èĩªçĦ¶
    0.06
     bothered
    0.06
     Pills
    0.06
    å°¸
    0.06
    дж
    0.05
    Activations Density 0.021%

    No Known Activations