© 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. 20850
    Prev
    Next
    INDEX
    Explanations

    second / type / set / version / aim / phase / embodiment / group / column

    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
    isy
    -0.05
    è¿Ļ
    -0.05
    HV
    -0.05
    æļĹ
    -0.05
    ingle
    -0.05
    atap
    -0.04
    转è§Ĵ
    -0.04
     Heg
    -0.04
    og
    -0.04
    heit
    -0.04
    POSITIVE LOGITS
     lagi
    0.07
    ën
    0.07
     **‘
    0.06
    âĢ¦the
    0.06
    çļĦçīĪæľ¬
    0.06
    авли
    0.06
    backs
    0.06
     &_
    0.06
    æij§
    0.06
    çĶ±è¢«åijĬ
    0.06
    Activations Density 0.026%

    No Known Activations