© 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. 21843
    Prev
    Next
    INDEX
    Explanations

    beginning

    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
    jent
    -0.05
     constr
    -0.05
    æľŁä¸Ń
    -0.05
    XT
    -0.05
    voud
    -0.05
    æĹłæĦ§
    -0.05
    ().
    -0.05
    gy
    -0.05
     proprietary
    -0.05
     Lair
    -0.05
    POSITIVE LOGITS
    zie
    0.06
     ![
    0.06
    ameron
    0.06
    ecke
    0.05
    ilden
    0.05
    ambat
    0.05
    çŃĶ
    0.05
    êté
    0.05
    tez
    0.05
    éģģ
    0.05
    Activations Density 0.006%

    No Known Activations