© 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. 20843
    Prev
    Next
    INDEX
    Explanations

    going against or opposite

    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
    æľīæѤ
    -0.05
    å¨
    -0.05
    resh
    -0.05
    lay
    -0.05
    na
    -0.05
    abb
    -0.05
    æŁij
    -0.05
     liken
    -0.05
    ÑĤÑĢÑĥ
    -0.05
    es
    -0.04
    POSITIVE LOGITS
     verf
    0.08
    veren
    0.07
     doÄŁr
    0.06
    ãĤĤãĤĬ
    0.06
     misd
    0.06
    centre
    0.06
    认å®ļ
    0.06
    chein
    0.06
     misc
    0.06
    uchten
    0.06
    Activations Density 0.003%

    No Known Activations