© 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. 20655
    Prev
    Next
    INDEX
    Explanations

    how to use

    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
    æīĵæī°
    -0.07
    å¹´å°Ĩ
    -0.06
    æĭīæĸ¯
    -0.06
    æĭīæĭī
    -0.06
    alin
    -0.06
    ?url
    -0.06
    ])==
    -0.06
    âĢ¦âĢ¦ãĢĤ
    -0.06
    anh
    -0.06
    éĻ¸
    -0.06
    POSITIVE LOGITS
    k
    0.06
    f
    0.06
     involved
    0.05
    ware
    0.05
    elle
    0.05
    el
    0.05
    d
    0.05
    c
    0.05
    case
    0.05
    p
    0.05
    Activations Density 0.001%

    No Known Activations