© 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. 18156
    Prev
    Next
    INDEX
    Explanations

    inform or report any

    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
    ár
    -0.06
    onso
    -0.06
    oben
    -0.06
    gent
    -0.05
    ars
    -0.05
    classes
    -0.05
    ä¸įå½ĵ
    -0.05
    åĩº
    -0.05
    é¢
    -0.05
    çŃīä»Ģä¹Ī
    -0.05
    POSITIVE LOGITS
    alit
    0.06
    æľīæŶ
    0.06
     conviv
    0.05
    umpa
    0.05
    isci
    0.05
     registrering
    0.05
    anted
    0.05
    æľīæĻĤ
    0.05
    <Role
    0.05
    æĮģä¹ħ
    0.05
    Activations Density 0.002%

    No Known Activations