© 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. 17061
    Prev
    Next
    INDEX
    Explanations

    finding counter

    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
    aknya
    -0.05
    ig
    -0.05
    åįİä¸Ń
    -0.05
    é¦ĸ
    -0.05
    antly
    -0.05
    IG
    -0.05
    çĶ±åIJĦ
    -0.05
    лено
    -0.05
    VS
    -0.05
    è¾Ł
    -0.04
    POSITIVE LOGITS
     **.**
    0.06
    egers
    0.06
    oya
    0.06
    ebed
    0.06
     Administra
    0.06
     org
    0.06
    oby
    0.06
    ?s
    0.06
    .Linked
    0.06
    ìŀĶ
    0.06
    Activations Density 0.001%

    No Known Activations