© 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. 18255
    Prev
    Next
    INDEX
    Explanations

    adverse reaction

    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
    heen
    -0.06
    ие
    -0.06
    iedad
    -0.06
    ensitivity
    -0.06
    .au
    -0.06
    ÑıзÑĭ
    -0.06
    Ñģловно
    -0.06
    umumkan
    -0.06
    anmoins
    -0.06
    ibling
    -0.05
    POSITIVE LOGITS
    er
    0.10
    ÑĢав
    0.08
    ter
    0.07
    arde
    0.07
    lou
    0.06
    erst
    0.06
    tern
    0.06
    eret
    0.06
    ER
    0.06
    gether
    0.06
    Activations Density 0.004%

    No Known Activations