© 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. 18827
    Prev
    Next
    INDEX
    Explanations

    in sequences of words

    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
    ÑģÑĤеÑģÑĤвенно
    -0.06
     Stor
    -0.06
    andom
    -0.06
     stor
    -0.05
    ä»»ä½ķ责任
    -0.05
    è£ħ
    -0.05
     bersangkutan
    -0.05
    æĹħ游度åģĩåĮº
    -0.05
    éĻ¤æѤ
    -0.05
    ®
    -0.05
    POSITIVE LOGITS
    ÅĤoży
    0.06
    TEE
    0.06
    lessly
    0.06
    åħ¬æīĢ
    0.06
    spread
    0.05
     annet
    0.05
     mene
    0.05
    ÑĮ
    0.05
    зоÑĢÑĥ
    0.05
    eful
    0.05
    Activations Density 0.019%

    No Known Activations