© 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. 20014
    Prev
    Next
    INDEX
    Explanations

    male and female distinctions

    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
    æ¤į
    -0.06
    æ°ijçļĦ
    -0.05
    è³Ĭ
    -0.05
    fl
    -0.05
    erp
    -0.05
    thr
    -0.05
     adapted
    -0.05
    人çļĦ
    -0.05
    æł¹æ·±
    -0.05
    oras
    -0.05
    POSITIVE LOGITS
    amaha
    0.06
    pron
    0.06
     sorr
    0.06
     Febru
    0.06
    à¹ģà¸ģà¹Ī
    0.06
    borough
    0.06
    å¤ļå°ijéĴ±
    0.06
    infras
    0.06
    heimer
    0.06
    oretical
    0.06
    Activations Density 0.043%

    No Known Activations