© 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. 21147
    Prev
    Next
    INDEX
    Explanations

    trying to or account

    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
    æĹĭ
    -0.06
    th
    -0.05
     remaining
    -0.05
     isolated
    -0.05
    åģļäºĽä»Ģä¹Ī
    -0.05
    S
    -0.05
     extended
    -0.04
    ä¿ĿçķĻ
    -0.04
    æľīæĦı
    -0.04
    ä¸įéĻIJäºİ
    -0.04
    POSITIVE LOGITS
    éģŃ
    0.06
    ammelt
    0.06
    keypress
    0.06
    åī¯åİħéķ¿
    0.06
    adesh
    0.06
    amour
    0.06
    lust
    0.06
    uslim
    0.06
    ="<<
    0.06
    ammen
    0.06
    Activations Density 0.002%

    No Known Activations