© 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. 21833
    Prev
    Next
    INDEX
    Explanations

    intraocular pressure, funding cuts, donor pool

    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
    icing
    -0.06
    顺便
    -0.06
    åıĪä¸Ģ
    -0.06
    را
    -0.05
     gu
    -0.05
    åĪļéľĢ
    -0.05
    tection
    -0.05
    iffin
    -0.05
     paramount
    -0.05
    anking
    -0.05
    POSITIVE LOGITS
    éĽ¯
    0.06
    lott
    0.06
    欢è¿İæĤ¨
    0.06
    åĽĽå±Ĥ
    0.06
    交æµģä¸İåIJĪä½ľ
    0.05
    ç´§éĹŃ
    0.05
     Knob
    0.05
     pity
    0.05
    ç³»ç»Łå°Ĩ
    0.05
    .call
    0.05
    Activations Density 0.043%

    No Known Activations