© 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. 17896
    Prev
    Next
    INDEX
    Explanations

    Let, What, rite

    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
    æľ¬æľº
    -0.07
    jala
    -0.07
     nhau
    -0.06
    icias
    -0.06
    äºĮéĥİ
    -0.06
     Autorin
    -0.06
    osan
    -0.06
    ierta
    -0.06
    weise
    -0.06
    åıĺæĽ´åIJİ
    -0.06
    POSITIVE LOGITS
    urn
    0.06
    vk
    0.05
    WC
    0.05
    OCO
    0.05
    _v
    0.05
    ou
    0.05
    çĽĨæł½
    0.05
     Coc
    0.05
    -v
    0.05
    ä¸İåIJĪä½ľ
    0.05
    Activations Density 0.006%

    No Known Activations