© 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. 21043
    Prev
    Next
    INDEX
    Explanations

    separators and list items

    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
    er
    -0.07
    an
    -0.07
    esch
    -0.07
    on
    -0.06
    et
    -0.06
    leased
    -0.06
    yard
    -0.06
    ан
    -0.06
    iems
    -0.06
    èĩ
    -0.06
    POSITIVE LOGITS
    ness
    0.07
    icer
    0.06
     viá»ĩc
    0.06
    tä
    0.06
    namen
    0.06
    	mkdir
    0.05
    ertype
    0.05
    ttä
    0.05
     ÑģебÑı
    0.05
    ÑģÑĤок
    0.05
    Activations Density 0.052%

    No Known Activations