© 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. 21769
    Prev
    Next
    INDEX
    Explanations

    G

    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
    ohnt
    -0.06
    åĥıä½ł
    -0.06
     Enti
    -0.06
    è¿ŀ
    -0.06
    ouble
    -0.06
    ادا
    -0.06
    ray
    -0.06
    halts
    -0.06
    åIJijè®°èĢħ
    -0.06
    ä¸įèĥľ
    -0.06
    POSITIVE LOGITS
    çĶŁåĮĸ
    0.05
    éra
    0.05
    atorium
    0.05
     panicked
    0.05
    _destroy
    0.05
    ä¼
    0.05
    æĽ¾åľ¨
    0.04
    fy
    0.04
    忧
    0.04
     sign
    0.04
    Activations Density 0.062%

    No Known Activations