© 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. 20399
    Prev
    Next
    INDEX
    Explanations

    chinese characters

    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
    веÑĢÑĪенÑģÑĤво
    -0.07
    ä¸įå¤ļçļĦ
    -0.07
    ibling
    -0.07
    rekli
    -0.07
    颱
    -0.07
    vely
    -0.06
    æĹłæĥħ
    -0.06
    endorf
    -0.06
    帮大家
    -0.06
    åĩºä¸į
    -0.06
    POSITIVE LOGITS
    b
    0.06
    o
    0.05
    å¯Ħ
    0.05
    è¯ģ
    0.05
    ï¼Ľ
    0.05
    å«©
    0.05
    åĺī
    0.05
     unders
    0.05
    _
    0.05
    tt
    0.05
    Activations Density 0.016%

    No Known Activations