© 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. 18182
    Prev
    Next
    INDEX
    Explanations

    wherein a

    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
    igned
    -0.06
    -going
    -0.06
     Blasio
    -0.06
    æľīä½ķ
    -0.06
     intended
    -0.05
    pok
    -0.05
    abouts
    -0.05
    éĤ£ä¸¤ä¸ª
    -0.05
    nish
    -0.05
    å¼Ħæ¸ħ
    -0.05
    POSITIVE LOGITS
    urve
    0.06
    æĪĸèĢħæľī
    0.06
    eree
    0.05
    ard
    0.05
    zie
    0.05
    åĽłä¸ºæľī
    0.05
    åĽłä¸ºè¿Ļ个
    0.05
    ä¹ī
    0.05
    ã
    0.05
    neau
    0.05
    Activations Density 0.029%

    No Known Activations