© 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. 19222
    Prev
    Next
    INDEX
    Explanations

    historical, editing, data, rewritten

    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
    سبب
    -0.06
     Disclosure
    -0.06
    åĻ¨çŃī
    -0.05
    иÑĢо
    -0.05
    迪æĸ¯
    -0.05
    诸天
    -0.05
    çıį妮
    -0.05
    InputLabel
    -0.05
     Conce
    -0.05
     Compr
    -0.05
    POSITIVE LOGITS
    çĶ·
    0.06
    vente
    0.06
    olo
    0.06
    éĨī
    0.06
    bang
    0.06
    ible
    0.05
    interested
    0.05
    认为
    0.05
    éļħ
    0.05
    pany
    0.05
    Activations Density 0.106%

    No Known Activations