© 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. 19280
    Prev
    Next
    INDEX
    Explanations

    inform someone / the

    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
    اجة
    -0.06
    غب
    -0.06
    ÄĻk
    -0.06
    enic
    -0.06
    enthal
    -0.05
    /license
    -0.05
    å±ķéĸĭ
    -0.05
    eron
    -0.05
    /top
    -0.05
    _super
    -0.05
    POSITIVE LOGITS
    ative
    0.07
    夷
    0.06
    odar
    0.06
    -Un
    0.06
    atted
    0.06
    æľĢç»ĪçļĦ
    0.06
    awks
    0.06
    оÑģо
    0.06
    ities
    0.06
    ؤÙĦاء
    0.06
    Activations Density 0.007%

    No Known Activations