© 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. 21441
    Prev
    Next
    INDEX
    Explanations

    due to

    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
    cky
    -0.06
    бÑĢе
    -0.06
    åľ¨æīĢ
    -0.06
    èĪµ
    -0.06
    ÙģتÙĩ
    -0.06
     ÑģÑı
    -0.05
    اÙģÙĬ
    -0.05
    semb
    -0.05
    ypes
    -0.05
    usunda
    -0.05
    POSITIVE LOGITS
     due
    0.16
    due
    0.15
    åĽł
    0.14
     Due
    0.14
    åĽłåħ¶
    0.13
     devido
    0.13
     debido
    0.13
    Due
    0.13
     بسبب
    0.13
    çĶ±äºİåħ¶
    0.12
    Activations Density 0.168%

    No Known Activations