© 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. 17120
    Prev
    Next
    INDEX
    Explanations

    lists and sequences

    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
    amn
    -0.06
    eed
    -0.05
    _
    -0.05
    æ¯Ķ
    -0.05
    çīĽ
    -0.05
    ç¾İ
    -0.05
    ew
    -0.05
    av
    -0.05
    çļ®
    -0.05
    ach
    -0.05
    POSITIVE LOGITS
     cso
    0.07
     Leverkus
    0.07
    cego
    0.07
    landes
    0.07
    ждÑĥÑİ
    0.07
     Sán
    0.06
     trien
    0.06
    _tC
    0.06
    lieben
    0.06
    hoff
    0.06
    Activations Density 5.603%

    No Known Activations