© 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. 20862
    Prev
    Next
    INDEX
    Explanations

    leadership and friendship development

    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
    oble
    -0.06
    uil
    -0.06
    ehm
    -0.06
    er
    -0.05
    ehör
    -0.05
    oire
    -0.05
    lepÅ¡ÃŃ
    -0.05
    oir
    -0.05
    enberg
    -0.05
    ighted
    -0.05
    POSITIVE LOGITS
    rio
    0.08
    s
    0.07
    rie
    0.07
    raga
    0.07
    sonian
    0.07
    輩
    0.07
    /company
    0.06
    ะ
    0.06
    éĺĻ
    0.06
    ÏĤ
    0.06
    Activations Density 0.031%

    No Known Activations