© 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. 21448
    Prev
    Next
    INDEX
    Explanations

    and I

    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
    osci
    -0.08
    orca
    -0.07
     séqu
    -0.07
    inhas
    -0.07
    oba
    -0.07
    osciuto
    -0.07
    ilhas
    -0.07
    живаеÑĤ
    -0.07
     dijal
    -0.07
    ä¹ĭ称
    -0.07
    POSITIVE LOGITS
    ing
    0.06
     man
    0.06
     ger
    0.05
     mens
    0.05
     :
    0.05
     ens
    0.05
    itud
    0.05
    ण
    0.05
    :
    0.05
     por
    0.05
    Activations Density 0.035%

    No Known Activations