© 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. 17034
    Prev
    Next
    INDEX
    Explanations

    watching tutorials or media

    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
    uthor
    -0.06
    upe
    -0.06
    éĤ
    -0.06
    ources
    -0.06
    请èģĶç³»åĪłéĻ¤
    -0.06
    å¾ij
    -0.06
    uges
    -0.06
    ága
    -0.06
     Zahl
    -0.06
    ahl
    -0.06
    POSITIVE LOGITS
    论
    0.06
    еÑĢед
    0.05
    åĨħ容åıĬ
    0.05
    æĦĪ
    0.05
    ist
    0.05
    设计æĸ¹æ¡Ī
    0.05
    åĨħ容ä¸İ
    0.05
    eno
    0.04
     contender
    0.04
    pt
    0.04
    Activations Density 0.004%

    No Known Activations