© 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. 21057
    Prev
    Next
    INDEX
    Explanations

    following or below

    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
    ered
    -0.06
    ÑĢеннÑĭм
    -0.06
     unica
    -0.05
    éģĵ
    -0.05
    çļ
    -0.05
    Ñĥжи
    -0.05
     deepest
    -0.05
    éĢĶ
    -0.05
    empo
    -0.05
    -first
    -0.05
    POSITIVE LOGITS
    ÐĺС
    0.06
    ogan
    0.05
    à¸Īริà¸ĩ
    0.05
    houette
    0.05
    pul
    0.05
    inqu
    0.05
    书ä¸Ń
    0.05
    çªľ
    0.05
     Bord
    0.05
    nit
    0.05
    Activations Density 0.032%

    No Known Activations