© 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. 17768
    Prev
    Next
    INDEX
    Explanations

    franchise titles followed by sequels

    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
    bre
    -0.07
    arranty
    -0.05
    çİ°å®ŀä¸Ń
    -0.05
    çĽ¸äº²
    -0.05
    èĤ¢
    -0.05
    èĪŀæĽ²
    -0.05
    BRE
    -0.05
    æħ°éĹ®
    -0.05
    iable
    -0.05
    ÑĥÑİ
    -0.05
    POSITIVE LOGITS
    ä¸ĢåĬ¨
    0.06
    åįĬè¾¹
    0.06
    utt
    0.06
    ç»ĵæŀĦåĮĸ
    0.06
    abel
    0.06
     phái
    0.06
    ä¸Ģå¸Ĩ
    0.05
    çīĪ
    0.05
     iner
    0.05
    ä¸Ń段
    0.05
    Activations Density 0.006%

    No Known Activations