© 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. 19205
    Prev
    Next
    INDEX
    Explanations

    film director names

    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
    ame
    -0.06
    ä¹ĭ交
    -0.06
    aim
    -0.06
    ë£Į
    -0.06
    iel
    -0.06
     aim
    -0.06
    ulet
    -0.06
    åĪ»æĦı
    -0.06
    è¿ĩå¤ľ
    -0.05
    lass
    -0.05
    POSITIVE LOGITS
    è´§
    0.06
    encent
    0.06
     ust
    0.05
    åħĦ
    0.05
    å¤Ħ以
    0.05
    å¤ĦçļĦ
    0.05
    bru
    0.05
    BRE
    0.05
    èĦijæ´ŀ
    0.05
     branching
    0.05
    Activations Density 0.105%

    No Known Activations