© 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. 17600
    Prev
    Next
    INDEX
    Explanations

    pull request, ruption cyst, manifest package, odontic

    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
    liz
    -0.07
    rels
    -0.07
    éłĥãģ¯
    -0.07
    agentur
    -0.07
    -pocket
    -0.07
     Klient
    -0.07
     Telefone
    -0.07
    ÑĢене
    -0.07
    èµ·è§ģ
    -0.07
    èĥĢ
    -0.07
    POSITIVE LOGITS
     cr
    0.05
    er
    0.05
     ar
    0.05
    cr
    0.05
    dy
    0.05
     cran
    0.04
     plasma
    0.04
     scrutin
    0.04
    æĶ¿æ²»
    0.04
    ib
    0.04
    Activations Density 0.010%

    No Known Activations