© 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. 21503
    Prev
    Next
    INDEX
    Explanations

    scientific terms and entities

    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
    -0.07
    elman
    -0.06
    ibil
    -0.06
    _f
    -0.06
    gge
    -0.05
    otos
    -0.05
    è¿ijçݰ代
    -0.05
    жеÑĢе
    -0.05
    _g
    -0.05
    สัม
    -0.05
    POSITIVE LOGITS
    benar
    0.06
    使å®ĥ
    0.06
     бо
    0.06
    çĹħæĤ£èĢħ
    0.05
    rai
    0.05
    колÑĮ
    0.05
     phu
    0.05
    Ce
    0.05
    ä»»
    0.05
     preciso
    0.05
    Activations Density 0.024%

    No Known Activations