© 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. 18339
    Prev
    Next
    INDEX
    Explanations

    process/reaction suffixes

    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
    elde
    -0.07
    ighth
    -0.07
    णि
    -0.07
    icali
    -0.07
    æĥ¯äºĨ
    -0.07
     bando
    -0.06
    arel
    -0.06
    ekon
    -0.06
    å¾Ĺèµ·
    -0.06
     ngại
    -0.06
    POSITIVE LOGITS
    Touches
    0.06
    åħ¨
    0.05
    åĶĩ
    0.05
    uletzt
    0.05
    J
    0.05
    çĮĽ
    0.05
    z
    0.05
    B
    0.05
    便
    0.05
     trải
    0.05
    Activations Density 0.014%

    No Known Activations