© 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. 19393
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    শ
    -0.06
    æĪĸå¤ļæĪĸå°ij
    -0.05
    oi
    -0.05
     Shank
    -0.05
    åħīæłĩ
    -0.05
    æ±ĩ
    -0.05
    our
    -0.05
    aise
    -0.05
    ª
    -0.05
    usto
    -0.05
    POSITIVE LOGITS
    inian
    0.06
    º¼
    0.06
    ç»´å°Ķ
    0.06
    amana
    0.06
    tester
    0.06
    atil
    0.06
    bere
    0.05
    igo
    0.05
     adh
    0.05
    cape
    0.05
    Activations Density 0.062%

    No Known Activations