© 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. 20543
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    åħ¶ä»ĸåªĴä½ĵ
    -0.06
    aver
    -0.06
    iscal
    -0.06
    istin
    -0.06
    tl
    -0.06
    Such
    -0.06
    _bias
    -0.05
    epend
    -0.05
     polite
    -0.05
    ÑĨиÑĤ
    -0.05
    POSITIVE LOGITS
    pto
    0.06
    uffer
    0.05
    /
    0.05
    pie
    0.05
    äºĮèĢħ
    0.05
    åı¸
    0.05
    mah
    0.05
    麻èĬ±
    0.05
     ()=>
    0.05
    tru
    0.05
    Activations Density 0.003%

    No Known Activations