© 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. 21190
    Prev
    Next
    INDEX
    Explanations

    bodily fluids and leaks

    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
    æħİéĩį
    -0.06
    immel
    -0.05
     bul
    -0.05
    æļĤæŶ
    -0.05
     Armour
    -0.05
     armour
    -0.05
     strained
    -0.05
    åĬłå¼ºä¸İ
    -0.05
    ought
    -0.05
    å©·
    -0.05
    POSITIVE LOGITS
    abouts
    0.07
    ụy
    0.05
    loch
    0.05
    ÑģÑĤÑĭ
    0.05
    jo
    0.05
    æ¶Īæģ¯ç§°
    0.05
    comed
    0.05
    emoc
    0.05
     själv
    0.05
    adop
    0.05
    Activations Density 0.001%

    No Known Activations