© 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. 18364
    Prev
    Next
    INDEX
    Explanations

    knowledge and comprehension

    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
    رÙĪÙĨ
    -0.06
     enchant
    -0.06
    Ñĥди
    -0.06
    renom
    -0.06
     itself
    -0.06
     Moody
    -0.06
    ielding
    -0.06
    ç©į
    -0.05
     záp
    -0.05
    åĵªå®¶
    -0.05
    POSITIVE LOGITS
     ÑĢÑĥбе
    0.06
     deeper
    0.06
     sanity
    0.05
    大ä¹ī
    0.05
     Review
    0.05
    stdbool
    0.05
    æ·±å±Ĥ
    0.05
    kah
    0.05
    æµħ
    0.05
    å¿ħé¡»æĺ¯
    0.05
    Activations Density 0.014%

    No Known Activations