© 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. 17128
    Prev
    Next
    INDEX
    Explanations

    album content tags

    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
    约æĿŁ
    -0.05
    for
    -0.05
     powerful
    -0.05
    High
    -0.05
     conceived
    -0.05
    foot
    -0.05
    åħ³éĶ®æĺ¯
    -0.05
    ver
    -0.04
     raise
    -0.04
     zar
    -0.04
    POSITIVE LOGITS
    plete
    0.08
    OLID
    0.07
    istere
    0.06
     mili
    0.06
    گراÙĨ
    0.06
    veg
    0.06
    à¹Ģหย
    0.06
    æĹłæĦ§
    0.06
    ISTRA
    0.06
     tir
    0.06
    Activations Density 0.024%

    No Known Activations