© 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. 18669
    Prev
    Next
    INDEX
    Explanations

    film/game ratings

    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
    PIP
    -0.06
     being
    -0.05
    iÃŁ
    -0.05
    odel
    -0.05
    ëłģ
    -0.05
    -0.05
     Lowe
    -0.05
     along
    -0.05
     certain
    -0.05
    athy
    -0.05
    POSITIVE LOGITS
    åĬŀç¨İ
    0.06
    -rating
    0.06
    eder
    0.06
    ämt
    0.06
    estr
    0.06
    å®ļåŀĭ
    0.06
     Patr
    0.06
    θεν
    0.06
    ardino
    0.06
    tav
    0.06
    Activations Density 0.003%

    No Known Activations