© 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. 17539
    Prev
    Next
    INDEX
    Explanations

    college outfits for guys

    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
    æľīåħ³äºİ
    -0.06
     اÙĦÙĤادÙħ
    -0.05
    çľĭåIJijäºĨ
    -0.05
    alic
    -0.05
    al
    -0.05
    Again
    -0.05
    av
    -0.05
    à¸ģำ
    -0.05
    f
    -0.05
    ØŃØ«
    -0.05
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.06
    лÑıн
    0.06
    resses
    0.06
     pano
    0.06
    ocere
    0.06
    trato
    0.06
    halts
    0.06
    éģ½
    0.06
    ÑĢÑĥп
    0.06
    stoff
    0.05
    Activations Density 0.001%

    No Known Activations