© 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. 20838
    Prev
    Next
    INDEX
    Explanations

    one more context

    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
    æĺ¯å¥½
    -0.06
    约æľī
    -0.05
    ಲà³įಲ
    -0.05
    adat
    -0.05
     começam
    -0.05
    äºĮåı·
    -0.05
     quite
    -0.05
    å°´å°¬
    -0.05
    å¼Ģå§ĭ
    -0.05
     rather
    -0.05
    POSITIVE LOGITS
    itten
    0.06
    dav
    0.06
    fulness
    0.06
    isons
    0.06
    妥
    0.06
    Before
    0.06
    _before
    0.06
    evity
    0.05
     remaining
    0.05
    çIJĨçĶ±
    0.05
    Activations Density 0.017%

    No Known Activations