© 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. 21368
    Prev
    Next
    INDEX
    Explanations

    but followed by contrastive clauses

    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
    uly
    -0.06
    ÙĨداÙĨ
    -0.06
    æľªå¿ħ
    -0.06
    ÑĪов
    -0.06
    è®°èĢħä»İ
    -0.06
    uwen
    -0.06
    空
    -0.06
    wurf
    -0.06
    würd
    -0.05
     fruta
    -0.05
    POSITIVE LOGITS
    onis
    0.06
    涵
    0.05
    andle
    0.05
    ewnÄĻ
    0.05
    imm
    0.05
    CAT
    0.05
    Ø¢ÙĨ
    0.05
     fore
    0.05
    jav
    0.05
    ume
    0.05
    Activations Density 0.018%

    No Known Activations