© 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. 21459
    Prev
    Next
    INDEX
    Explanations

    advisor, coach, or consultant names

    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
    icky
    -0.07
    åıĺ
    -0.06
    æĺ¯éĽĨ
    -0.06
    ä»ĵ
    -0.06
    Ñĩайно
    -0.06
    çŃĴ
    -0.06
    [:,:,
    -0.06
    mens
    -0.06
     comp
    -0.06
    çŃĨ
    -0.06
    POSITIVE LOGITS
    ìĦ¤
    0.06
     adviser
    0.06
    Advisor
    0.06
     Coaching
    0.06
     Warning
    0.06
    è´¹çĶ¨çĶ±
    0.06
    èѦåijĬ
    0.06
    ä¸Ĭ身
    0.05
     advisor
    0.05
    amet
    0.05
    Activations Density 0.033%

    No Known Activations