© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19835
    Prev
    Next
    INDEX
    Explanations

    artistic descriptions, architectural concepts, specific objects

    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
    çīĩ
    -0.06
    alysis
    -0.06
    inken
    -0.06
     accompagnement
    -0.06
    lient
    -0.06
    usern
    -0.06
     acquis
    -0.06
    peration
    -0.06
    locker
    -0.06
    ä¸įåľ¨ä¹İ
    -0.06
    POSITIVE LOGITS
    hide
    0.05
    abor
    0.05
    çļĦæ¦Ĥ念
    0.05
    åīį款
    0.05
    æ¯ı个人éĥ½æľī
    0.05
    æ¦Ĥ念
    0.05
    æ¯ı个
    0.05
     meeting
    0.05
    åijµåijµ
    0.05
    posit
    0.05
    Activations Density 0.002%

    No Known Activations