© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21223
    Prev
    Next
    INDEX
    Explanations

    speech recognition or synthesizer

    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
    rike
    -0.06
    mine
    -0.06
    çļĦ人士
    -0.06
    æĶ»åħĭ
    -0.06
    /original
    -0.06
    วิà¸Ĭา
    -0.06
    anud
    -0.05
    uite
    -0.05
    åĶ¤
    -0.05
    éĵĽ
    -0.05
    POSITIVE LOGITS
     recurrent
    0.06
    worthy
    0.06
    заÑĢ
    0.05
     rumbo
    0.05
     inflation
    0.05
    بØŃ
    0.05
     ÏĢίÏĥ
    0.05
    èĨ¨èĥĢ
    0.05
    halten
    0.05
     Splash
    0.05
    Activations Density 0.001%

    No Known Activations