© 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. 21695
    Prev
    Next
    INDEX
    Explanations

    kids

    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
    ian
    -0.06
     sym
    -0.06
    ä¸įçĦ¶
    -0.06
     elles
    -0.05
    人æīį
    -0.05
    полни
    -0.05
     Elles
    -0.05
    çĽĪ
    -0.05
     diá»ħn
    -0.05
    sym
    -0.05
    POSITIVE LOGITS
    emas
    0.06
    大红
    0.06
     flott
    0.06
     dig
    0.06
    ç±»çŃī
    0.06
    loom
    0.06
    ["+
    0.06
    dig
    0.05
    ocs
    0.05
     cand
    0.05
    Activations Density 0.074%

    No Known Activations