© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20745
    Prev
    Next
    INDEX
    Explanations

    person or victim reference

    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
    schlä
    -0.06
     nÆ°Æ¡ng
    -0.06
     themselves
    -0.06
     alike
    -0.06
    lent
    -0.06
    vr
    -0.06
    weise
    -0.06
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    -0.06
    orsch
    -0.06
    åĢŁåĬĽ
    -0.06
    POSITIVE LOGITS
    å¹²
    0.05
    reet
    0.05
    agraph
    0.05
    åĬŀçļĦ
    0.05
    itution
    0.05
    å²ģéĤ£å¹´
    0.05
    cket
    0.05
     ceb
    0.05
    .UR
    0.05
    oken
    0.05
    Activations Density 0.005%

    No Known Activations