© 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. 17890
    Prev
    Next
    INDEX
    Explanations

    alternative or opposite

    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
    ãĤĪãĤĬ
    -0.05
    èĶ
    -0.05
     h
    -0.05
     fal
    -0.05
    igny
    -0.05
    åĢ¾
    -0.05
     более
    -0.05
    广
    -0.05
    erty
    -0.05
    indle
    -0.05
    POSITIVE LOGITS
    æĻ®åĪ©
    0.06
    شاء
    0.06
    ehlen
    0.06
    Å¡i
    0.06
    lest
    0.06
    leder
    0.06
    ÑĪем
    0.05
     Zobacz
    0.05
    åĬij
    0.05
    ÅŁi
    0.05
    Activations Density 0.097%

    No Known Activations