© 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. 22124
    Prev
    Next
    INDEX
    Explanations

    negotiating

    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
    ness
    -0.07
     *:
    -0.07
    ohan
    -0.06
    δο
    -0.06
    ngo
    -0.06
    sstr
    -0.06
    äºİæѤ
    -0.06
    æĪ¿çļĦ
    -0.06
    inkel
    -0.06
    ogram
    -0.06
    POSITIVE LOGITS
    ile
    0.06
    abor
    0.05
    affles
    0.05
    ight
    0.05
    iles
    0.05
    iot
    0.05
    æĺ¯åIJ¦åŃĺåľ¨
    0.05
    ä»Ģä¹Īåij¢
    0.05
    æıIJéĨĴ大家
    0.05
    gien
    0.05
    Activations Density 0.010%

    No Known Activations