© 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. 21352
    Prev
    Next
    INDEX
    Explanations

    truthfulness of statements

    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
    ä¸ĵ
    -0.06
    def
    -0.05
    lect
    -0.05
    å¿Ĺ
    -0.05
    ->
    -0.05
    v
    -0.05
    åħ³
    -0.05
    eval
    -0.05
    lo
    -0.05
     lot
    -0.04
    POSITIVE LOGITS
    ulich
    0.07
    ulti
    0.07
    æł·çļĦ
    0.06
    orest
    0.06
    éºŁ
    0.06
    åı¯èĥ½æĺ¯åĽłä¸º
    0.06
    abora
    0.06
    åºŁè¯Ŀ
    0.06
    reet
    0.06
    ynu
    0.06
    Activations Density 0.012%

    No Known Activations