© 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. 21238
    Prev
    Next
    INDEX
    Explanations

    Label, size, or sex context

    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
    itus
    -0.06
    ume
    -0.06
    mc
    -0.05
    Fir
    -0.05
    yle
    -0.05
    å®Ŀå±±
    -0.05
    imat
    -0.05
    orsi
    -0.05
    ky
    -0.05
    acies
    -0.05
    POSITIVE LOGITS
    trup
    0.07
    áĥĹáĥIJáĥľ
    0.06
    ebilecek
    0.06
    大æīĭ
    0.06
    zil
    0.06
    hind
    0.06
    inkan
    0.05
    ä¸Ģæĸĩ
    0.05
    åľ¨é«ĺéĢŁåħ¬è·¯
    0.05
    åĨķ
    0.05
    Activations Density 0.003%

    No Known Activations