© 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. 20412
    Prev
    Next
    INDEX
    Explanations

    Pacific Rim, specific titles, Angel Club

    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
    ois
    -0.07
    çĶŁçIJĨ
    -0.07
    精度é«ĺ
    -0.06
    живание
    -0.06
    ç
    -0.06
    erties
    -0.06
    è¿ijå¹³
    -0.06
    æ¯ĴæĢ§
    -0.06
    olet
    -0.06
    æīĵåIJ¬
    -0.06
    POSITIVE LOGITS
     junk
    0.06
    ç¤ģ
    0.06
    Mobil
    0.05
     fortified
    0.05
    ie
    0.05
    junk
    0.05
    سخ
    0.05
    otte
    0.05
     conglomer
    0.05
    æĢ
    0.05
    Activations Density 0.014%

    No Known Activations