© 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. 18336
    Prev
    Next
    INDEX
    Explanations

    work models, theory, terminology, history, questions

    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®
    -0.07
     лÑĥка
    -0.06
    leden
    -0.06
    ajos
    -0.06
    iori
    -0.06
     завÑĤÑĢа
    -0.06
    дал
    -0.06
     cáºŃn
    -0.06
    Forget
    -0.06
    loor
    -0.06
    POSITIVE LOGITS
    éĶĻ
    0.05
    æļĹ
    0.05
    iesz
    0.05
    ÙĩÙĨ
    0.05
    æķŀ
    0.05
    qh
    0.05
    çĸijä¼¼
    0.05
    客
    0.05
    aci
    0.05
     Nicholson
    0.05
    Activations Density 0.067%

    No Known Activations