© 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. 19189
    Prev
    Next
    INDEX
    Explanations

    let me know if you have questions

    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
    ffer
    -0.06
    lot
    -0.06
     opin
    -0.06
     ogen
    -0.06
    æıIJéĨĴ
    -0.06
    æ¸ħæ¸ħ
    -0.05
    lend
    -0.05
    è¿ľéĶĢ
    -0.05
     conscient
    -0.05
    aka
    -0.05
    POSITIVE LOGITS
    conde
    0.06
    insel
    0.06
     Fäh
    0.05
    å¾ĪåıĹ
    0.05
    éľĢè¦ģå°Ĩ
    0.05
    èĥ½åĬĽæıIJåįĩ
    0.05
     Cummings
    0.05
     facets
    0.05
    çĩĥçĥ§çļĦ
    0.05
    ذاب
    0.05
    Activations Density 0.006%

    No Known Activations