© 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. 20563
    Prev
    Next
    INDEX
    Explanations

    version of

    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
    anak
    -0.07
    keit
    -0.06
    ALLY
    -0.06
    /current
    -0.06
    /desktop
    -0.06
    isode
    -0.05
    riff
    -0.05
     unpopular
    -0.05
    fasst
    -0.05
    oad
    -0.05
    POSITIVE LOGITS
    roy
    0.06
     tang
    0.06
    atis
    0.06
    áĥĿáĥł
    0.05
    obot
    0.05
    使çĶ¨åIJİ
    0.05
    ÅŁe
    0.05
    idth
    0.05
    wealth
    0.05
    orph
    0.05
    Activations Density 0.011%

    No Known Activations