© 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. 17084
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific following words

    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
    溯
    -0.07
    suit
    -0.06
    Suit
    -0.06
    atars
    -0.06
    reau
    -0.06
    ertain
    -0.06
    å°±æĺ¯ä¸į
    -0.06
    ünftig
    -0.06
    atable
    -0.06
     SOME
    -0.06
    POSITIVE LOGITS
    alit
    0.05
    bach
    0.05
    eth
    0.05
    press
    0.05
    jen
    0.05
    æĪij便
    0.05
    emann
    0.05
    agt
    0.05
    éĥ½åĢ¼å¾Ĺ
    0.05
    jing
    0.05
    Activations Density 0.001%

    No Known Activations