© 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. 17317
    Prev
    Next
    INDEX
    Explanations

    parent relationships

    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
    iggins
    -0.06
    大夫
    -0.06
    ulti
    -0.06
    oner
    -0.06
    POINTS
    -0.06
    porte
    -0.06
    onto
    -0.06
    ive
    -0.06
    大ä¹ĺ
    -0.05
    ions
    -0.05
    POSITIVE LOGITS
    lah
    0.06
    enum
    0.06
    ence
    0.06
    รวà¸Ķ
    0.06
    t
    0.06
     estat
    0.06
    ä¸ĢåĪĩçļĦ
    0.06
    ä½Ĩè¿ĺæĺ¯
    0.05
    ä¸Ģç³»åĪĹçļĦ
    0.05
    زÙĩ
    0.05
    Activations Density 0.014%

    No Known Activations