© 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. 19057
    Prev
    Next
    INDEX
    Explanations

    cephalosporins and penicillins

    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
    ä½ĻçĥŃ
    -0.06
     toasted
    -0.06
     ash
    -0.06
    .Home
    -0.05
     heat
    -0.05
     immortal
    -0.05
    å°¼åħĭæĸ¯
    -0.05
    home
    -0.05
    éĿĵ
    -0.05
     дно
    -0.05
    POSITIVE LOGITS
    arks
    0.06
    akest
    0.06
    çIJ¶
    0.06
    ä¿IJ
    0.06
     cors
    0.06
    arate
    0.06
    ç¬
    0.05
    vue
    0.05
    个åŃIJ
    0.05
    odont
    0.05
    Activations Density 0.014%

    No Known Activations