© 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. 17927
    Prev
    Next
    INDEX
    Explanations

    pronoun + action verb

    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
     adj
    -0.05
    åijĬ
    -0.05
     bon
    -0.05
     G
    -0.05
     promis
    -0.05
    å¤į
    -0.05
     http
    -0.04
     modified
    -0.04
    éģį
    -0.04
    é»ijåIJįåįķ
    -0.04
    POSITIVE LOGITS
    ologis
    0.07
    tagon
    0.07
    壹
    0.07
    chap
    0.07
    olong
    0.06
    hyd
    0.06
    bern
    0.06
    Ä«b
    0.06
    åIJ«éĩı
    0.06
    resent
    0.06
    Activations Density 0.001%

    No Known Activations