© 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. 17860
    Prev
    Next
    INDEX
    Explanations

    fear, anxiety, phobias

    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
    andra
    -0.06
     Wirk
    -0.05
     creative
    -0.05
    oint
    -0.05
     mes
    -0.05
     Confira
    -0.05
    piel
    -0.05
     drift
    -0.05
     oscill
    -0.05
     sculpt
    -0.05
    POSITIVE LOGITS
    é¢ĦåħĪ
    0.06
    μÏĨ
    0.06
    ẫn
    0.06
    PERT
    0.06
    loo
    0.06
     expo
    0.06
    ilation
    0.06
    æĹłçķı
    0.06
    еÑĤи
    0.05
     Ðŀде
    0.05
    Activations Density 0.010%

    No Known Activations