© 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. 20231
    Prev
    Next
    INDEX
    Explanations

    holding, gripping, jaws, bucket, fork

    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
    Âł
    -0.06
    è´¼
    -0.06
     rol
    -0.05
    !
    -0.05
    пол
    -0.05
    åıijçĥŃ
    -0.05
    éħ
    -0.05
     Mol
    -0.05
     chor
    -0.05
     sc
    -0.05
    POSITIVE LOGITS
    anam
    0.07
    ubl
    0.07
     Valenci
    0.07
    знаком
    0.07
    ç½
    0.07
    utsch
    0.06
    æĹłè¯Ń
    0.06
    åį°
    0.06
    ubah
    0.06
     اÙĦرØŃ
    0.06
    Activations Density 0.031%

    No Known Activations