© 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. 20339
    Prev
    Next
    INDEX
    Explanations

    leader changes and appointments

    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
     recently
    -0.06
    recent
    -0.06
    èĪį
    -0.06
    使å®ĥ
    -0.06
    prototype
    -0.06
     lately
    -0.05
    åģ¶å°Ķ
    -0.05
    使ä¹ĭ
    -0.05
     prochaines
    -0.05
    åݻ年
    -0.05
    POSITIVE LOGITS
    etur
    0.06
    avier
    0.05
     defer
    0.05
    ogen
    0.05
    Motion
    0.05
     ajusta
    0.05
    ifica
    0.05
    ÑİÑĢ
    0.05
    åĬ¿åľ¨å¿ħ
    0.05
    ber
    0.05
    Activations Density 0.020%

    No Known Activations