© 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. 19259
    Prev
    Next
    INDEX
    Explanations

    health, energy, communication, social, business, functional

    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
    lest
    -0.06
    æĪĸåĪ©çĶ¨
    -0.05
    lund
    -0.05
    人æĪĸ
    -0.05
    ople
    -0.05
    еÑģÑĮ
    -0.05
    ová
    -0.05
     protected
    -0.05
    anine
    -0.05
     Protected
    -0.05
    POSITIVE LOGITS
    acker
    0.06
    ÙĦاÙĤ
    0.05
    isle
    0.05
     Major
    0.05
    è§ĦåĪĴ纲è¦ģ
    0.05
     major
    0.05
    Hack
    0.05
    icule
    0.05
    å¡ijæĸĻè¢ĭ
    0.05
    éªĩ
    0.05
    Activations Density 0.124%

    No Known Activations