© 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. 17965
    Prev
    Next
    INDEX
    Explanations

    virgin, new, or sealed

    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
    urred
    -0.06
    æ°Ķ温
    -0.06
     eget
    -0.06
    ignet
    -0.06
    chiere
    -0.05
     اÙĦÙħز
    -0.05
    å¾Īå¿Ļ
    -0.05
    zny
    -0.05
    çĽ¸å¯¹æ¯Ķè¾ĥ
    -0.05
    gef
    -0.05
    POSITIVE LOGITS
    fore
    0.07
    ra
    0.06
    å¤ķ
    0.06
    re
    0.06
    ry
    0.05
    hold
    0.05
    ene
    0.05
    ä¸įæ²»
    0.05
    æij
    0.05
    ire
    0.05
    Activations Density 0.001%

    No Known Activations