© 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. 19773
    Prev
    Next
    INDEX
    Explanations

    change and conditions

    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
    墨水
    -0.06
    QS
    -0.06
    æݪ
    -0.06
    æķĻè®Ń
    -0.06
    INCLUDING
    -0.05
    artet
    -0.05
    hv
    -0.05
    à¸Ļิ
    -0.05
     Johns
    -0.05
    å´İå¸Ĥ
    -0.05
    POSITIVE LOGITS
    alam
    0.06
    urn
    0.06
    以åıĬåIJĦç§į
    0.06
     andato
    0.05
    atz
    0.05
    ä½ľä¸ºä¸Ģ款
    0.05
    使å¾Ĺ
    0.05
    astre
    0.05
    eft
    0.05
     vetr
    0.05
    Activations Density 0.104%

    No Known Activations