© 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. 17739
    Prev
    Next
    INDEX
    Explanations

    sally, sassy, sittings, sowing, siphon

    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
    ea
    -0.06
    Ñħ
    -0.06
    c
    -0.06
    h
    -0.06
    ik
    -0.06
    -0.06
    een
    -0.06
    ob
    -0.06
    eh
    -0.05
    p
    -0.05
    POSITIVE LOGITS
    trup
    0.08
    ialized
    0.08
    orto
    0.08
    amedi
    0.08
    agues
    0.08
    istrate
    0.07
    apore
    0.07
    pez
    0.07
    à¸Ĭิà¸ģ
    0.07
    akup
    0.07
    Activations Density 0.049%

    No Known Activations