© 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. 19044
    Prev
    Next
    INDEX
    Explanations

    John Gonzalez, John Gill

    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
    ione
    -0.06
    çĪĨäºĨ
    -0.06
    ourn
    -0.06
    ombo
    -0.06
    å¤į
    -0.06
     scientif
    -0.06
     artific
    -0.06
    worth
    -0.06
    æİĪ
    -0.06
     lho
    -0.06
    POSITIVE LOGITS
    /posts
    0.05
    .ravel
    0.05
    posts
    0.05
    åĨįçľĭçľĭ
    0.05
    inel
    0.05
    /latest
    0.04
    çIJħ
    0.04
    룩
    0.04
    侯
    0.04
    .Repository
    0.04
    Activations Density 0.001%

    No Known Activations