© 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. 21150
    Prev
    Next
    INDEX
    Explanations

    initial approach, reaction, knockout, cardiac

    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
    iance
    -0.05
    ish
    -0.05
    пиÑģание
    -0.05
    æľīçļĦæŶåĢĻ
    -0.05
    -minded
    -0.05
    account
    -0.05
    -ish
    -0.05
    li
    -0.05
    -day
    -0.05
    -state
    -0.04
    POSITIVE LOGITS
    chers
    0.08
    èĩªå·±çļĦåĬªåĬĽ
    0.08
    enko
    0.07
    er
    0.07
    olim
    0.07
    èĩªå·±çļĦæĥ³æ³ķ
    0.07
    erias
    0.07
    bol
    0.06
    ster
    0.06
    สà¹Į
    0.06
    Activations Density 0.012%

    No Known Activations