© 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. 20482
    Prev
    Next
    INDEX
    Explanations

    not working

    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
    许
    -0.06
    der
    -0.06
    è¿Ľä¸ĢæŃ¥çļĦ
    -0.05
    azzo
    -0.05
     Cutter
    -0.05
    å¥
    -0.05
     hopeful
    -0.05
    åıĪ好
    -0.05
    retta
    -0.05
    æ·
    -0.05
    POSITIVE LOGITS
    кÑĥп
    0.07
    urus
    0.06
    ürg
    0.06
    èĻ½çĦ¶æ²¡æľī
    0.06
    midi
    0.06
    Mvc
    0.06
    ilater
    0.06
    линг
    0.05
    UCT
    0.05
    ége
    0.05
    Activations Density 0.004%

    No Known Activations