© 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. 22159
    Prev
    Next
    INDEX
    Explanations

    misconception and ideas

    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
     سر
    -0.07
    elho
    -0.06
    weichen
    -0.06
    ulam
    -0.06
     already
    -0.06
    ijke
    -0.06
    embe
    -0.06
     Already
    -0.06
    ез
    -0.06
     Moreira
    -0.06
    POSITIVE LOGITS
    ibel
    0.06
    z
    0.05
    ondo
    0.05
    éĩijæ¦ľ
    0.05
     misconception
    0.05
    intel
    0.05
    liter
    0.05
    oba
    0.05
    碰æĴŀ
    0.05
    使
    0.05
    Activations Density 0.082%

    No Known Activations