© 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. 17738
    Prev
    Next
    INDEX
    Explanations

    asking for alternatives or options

    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
    anser
    -0.06
    åħ¬åı¸æĪIJåijĺ
    -0.05
    anse
    -0.05
     rece
    -0.05
    æ¿Ģ
    -0.05
    _reserved
    -0.05
    okus
    -0.05
     GRAT
    -0.05
     Senior
    -0.05
    å°¼æĸ¯
    -0.05
    POSITIVE LOGITS
     yourselves
    0.07
    whatever
    0.07
     none
    0.06
     whatever
    0.06
    åħ¨æĸ°çļĦ
    0.06
     herself
    0.06
    egen
    0.06
    none
    0.05
     ourselves
    0.05
     topped
    0.05
    Activations Density 0.020%

    No Known Activations