© 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. 20681
    Prev
    Next
    INDEX
    Explanations

    attracts customers or attention

    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
    们
    -0.06
    ç»Ĭ
    -0.06
    iena
    -0.06
    esy
    -0.06
    ç½Ĺæĭī
    -0.06
    èIJ½äºĨ
    -0.06
    erved
    -0.06
    ä»¬ä¹Ł
    -0.06
    zkod
    -0.06
    ÑħваÑĤи
    -0.06
    POSITIVE LOGITS
    he
    0.06
    0.06
    d
    0.05
    @mail
    0.05
    antic
    0.05
    atters
    0.05
    ze
    0.05
    åıijå±ķçļĦéľĢè¦ģ
    0.05
    ìŀ¬
    0.05
    aci
    0.05
    Activations Density 0.005%

    No Known Activations