© 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. 17266
    Prev
    Next
    INDEX
    Explanations

    US states

    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
    úd
    -0.06
    æŀŃ
    -0.06
    gó
    -0.06
     Erf
    -0.05
    é¦ĸæĺł
    -0.05
    åı¯æĮī
    -0.05
     manch
    -0.05
    impat
    -0.05
    æľīæķĪ
    -0.05
    utf
    -0.05
    POSITIVE LOGITS
    port
    0.06
    ville
    0.06
    idget
    0.06
    inti
    0.05
     übrig
    0.05
    wort
    0.05
    olls
    0.05
    itted
    0.05
    net
    0.05
    -based
    0.05
    Activations Density 0.052%

    No Known Activations