© 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. 20706
    Prev
    Next
    INDEX
    Explanations

    previous original

    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
    oin
    -0.06
    vah
    -0.05
    ith
    -0.05
    маÑħ
    -0.05
     Az
    -0.05
    az
    -0.05
    Az
    -0.05
    å§Ĭ
    -0.05
    innan
    -0.05
    igh
    -0.05
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.07
     portions
    0.07
    ä¸Ģéĥ¨åĪĨ
    0.06
    éĥ¨åĪĨ
    0.06
     parte
    0.06
     portion
    0.06
     Portions
    0.06
    éĥ¨åĪĨæĺ¯
    0.06
    ermen
    0.06
     parto
    0.06
    Activations Density 0.103%

    No Known Activations