© 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. 20082
    Prev
    Next
    INDEX
    Explanations

    explaining assumptions or arguments

    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
    trup
    -0.06
    å½ĵä¸ĭ
    -0.06
    adou
    -0.05
    ufs
    -0.05
    æĦı
    -0.05
    è¹
    -0.05
    çĶ£
    -0.05
    raf
    -0.05
    èĽ
    -0.05
    梳çIJĨ
    -0.05
    POSITIVE LOGITS
    iddles
    0.06
     appropriately
    0.05
    éĥ½æĺ¯èĩªå·±
    0.05
    è¦ĭç©į
    0.05
     appropriate
    0.05
    saan
    0.05
    çĪ±ç¾İ
    0.05
    çĶ¨å¾Ĺ
    0.05
     om
    0.05
    oron
    0.05
    Activations Density 0.006%

    No Known Activations