© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19389
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

    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
    å°±æľīåı¯èĥ½
    -0.06
     подвод
    -0.06
    seille
    -0.05
    ebbe
    -0.05
     prov
    -0.05
    atted
    -0.05
    ãģ§ãĤĤãģĤãĤĭ
    -0.05
    ystone
    -0.05
     renda
    -0.05
    tbody
    -0.05
    POSITIVE LOGITS
     cerebr
    0.06
    oe
    0.05
    aes
    0.05
    oo
    0.05
    éĴĪ对
    0.05
    _references
    0.05
    è½»
    0.05
    以æ±Ĥ
    0.05
    滥
    0.05
    اء
    0.05
    Activations Density 0.009%

    No Known Activations