© 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. 22225
    Prev
    Next
    INDEX
    Explanations

    having + gerund or past participle

    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
    iasi
    -0.06
    orate
    -0.06
    iante
    -0.06
    ç¬
    -0.06
    erti
    -0.06
    ryw
    -0.06
    icado
    -0.06
    ebu
    -0.06
    ç«ĭãģ¦
    -0.06
    oph
    -0.06
    POSITIVE LOGITS
    æ¯į
    0.06
    sein
    0.05
    м
    0.05
    ÏĥÏį
    0.05
    troppo
    0.05
    ãģ¾ãģ¾
    0.05
    ä¸Ģåĭº
    0.05
    å¤ļå°ij
    0.05
    tis
    0.05
    çĪ¶
    0.05
    Activations Density 0.026%

    No Known Activations