© 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. 16932
    Prev
    Next
    INDEX
    Explanations

    ask, say, tell, court decisions

    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
    æ°ı
    -0.06
    ÛĮزÛĮ
    -0.06
    ue
    -0.06
    èѬå¦Ĥ
    -0.05
    branches
    -0.05
    -go
    -0.05
    gee
    -0.05
    Ø©
    -0.05
    çļĦåIJĪæĪIJ
    -0.05
    branch
    -0.05
    POSITIVE LOGITS
    olated
    0.07
    ác
    0.07
    iÅĤ
    0.06
    oplan
    0.06
    atile
    0.05
    esthes
    0.05
    lipp
    0.05
    ÑħваÑĤ
    0.05
    utely
    0.05
    ãĥĥãĤŃ
    0.05
    Activations Density 0.001%

    No Known Activations