© 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. 21006
    Prev
    Next
    INDEX
    Explanations

    going to work

    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
    istr
    -0.05
    aj
    -0.05
    asen
    -0.05
    udy
    -0.05
    airo
    -0.05
     perk
    -0.05
    è¨Ī
    -0.05
    жил
    -0.05
    erden
    -0.05
    ouz
    -0.05
    POSITIVE LOGITS
    è±ģ
    0.07
    ılı
    0.06
    giv
    0.06
    åħ¬èĭ±
    0.06
    hors
    0.06
    islam
    0.06
    CIM
    0.06
    çīĪ车åŀĭ
    0.06
     yearly
    0.06
     annually
    0.05
    Activations Density 0.011%

    No Known Activations