© 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. 20946
    Prev
    Next
    INDEX
    Explanations

    In the

    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
    полне
    -0.06
    åľ¨åľº
    -0.06
     ours
    -0.06
     theirs
    -0.06
     airl
    -0.06
    ׳×Ļ×Ļ×Ŀ
    -0.06
    ÙħاÙħ
    -0.06
    mány
    -0.06
    terna
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    POSITIVE LOGITS
    uel
    0.06
    ify
    0.06
    çĥĪçļĦ
    0.06
    ings
    0.05
    åĵģçļĦ
    0.05
    onton
    0.05
    åĻ
    0.05
    vene
    0.05
    онÑĤ
    0.05
    heits
    0.05
    Activations Density 0.069%

    No Known Activations