© 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. 20187
    Prev
    Next
    INDEX
    Explanations

    data input

    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
    pect
    -0.06
    åĵ®
    -0.06
    æĭī
    -0.05
    åIJī祥çī©
    -0.05
    -abortion
    -0.05
    èį¯çī©æ²»çĸĹ
    -0.05
    Ûģ
    -0.05
    ly
    -0.05
    ello
    -0.05
    AnimationFrame
    -0.05
    POSITIVE LOGITS
    åħ¥äºĨ
    0.06
    åħ¥åĬĽ
    0.06
    oven
    0.06
    à¸ĸึà¸ĩà¸Ħวาม
    0.06
    resar
    0.06
    assis
    0.06
    llen
    0.06
    åĴĮç»´æĬ¤
    0.06
    UX
    0.06
    è¿Ľåİ»
    0.06
    Activations Density 0.013%

    No Known Activations