© 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. 21213
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    ambu
    -0.06
     lev
    -0.06
    angs
    -0.06
    кÑĢ
    -0.05
    еÑĢб
    -0.05
    æľ
    -0.05
     Lif
    -0.05
    Ïį
    -0.05
     bais
    -0.05
    æĺŃ
    -0.05
    POSITIVE LOGITS
    oot
    0.06
    åĩº
    0.05
    dling
    0.05
    åħī
    0.05
    åıijå±ķæĶ¹éĿ©
    0.05
    mals
    0.05
    å½±
    0.05
    çIJĨäºĭ
    0.05
    Back
    0.05
    mudah
    0.05
    Activations Density 0.005%

    No Known Activations