© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18424
    Prev
    Next
    INDEX
    Explanations

    call to action verbs

    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
    .
    -0.06
    -0.06
    u
    -0.06
    h
    -0.05
     ple
    -0.05
    èĭ¥æľī
    -0.05
    obj
    -0.05
    engu
    -0.05
    äºĨ
    -0.05
    j
    -0.05
    POSITIVE LOGITS
    -Nov
    0.07
    rippling
    0.06
     amat
    0.06
    åŀ¦
    0.06
    radient
    0.06
    razier
    0.06
     verst
    0.06
    olson
    0.06
    ashian
    0.06
    atson
    0.06
    Activations Density 0.053%

    No Known Activations