© 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. 19121
    Prev
    Next
    INDEX
    Explanations

    services and information

    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
    atelier
    -0.06
    liess
    -0.05
    ries
    -0.05
    çłĶ究åĴĮ
    -0.05
    anship
    -0.05
    -sdk
    -0.05
    EE
    -0.05
    ee
    -0.05
    hi
    -0.05
    izio
    -0.05
    POSITIVE LOGITS
    çĶ»
    0.06
    Complete
    0.05
    sbin
    0.05
    idr
    0.05
     statically
    0.05
    è½°
    0.05
    åİĭåĬĽå¤§
    0.05
    esty
    0.05
     Eval
    0.05
    æĻĴ
    0.05
    Activations Density 0.107%

    No Known Activations