© 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. 16940
    Prev
    Next
    INDEX
    Explanations

    `Map` `.add` `.erase` `.Set` `Event`

    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
    kommen
    -0.06
    容
    -0.06
    pop
    -0.05
    讳
    -0.05
    ossen
    -0.05
    fus
    -0.05
    un
    -0.05
    æĸĩ书
    -0.05
    еÑĤÑĮ
    -0.05
    æĪĸå¤ļ个
    -0.05
    POSITIVE LOGITS
    á»ĥn
    0.06
    بÙĤ
    0.05
    aways
    0.05
    érist
    0.05
     every
    0.05
    ä½ľåĵį
    0.05
     Every
    0.05
    ledon
    0.05
    ä¸ĭæĮ«
    0.05
    å±±æĻ¯åĮº
    0.05
    Activations Density 0.011%

    No Known Activations