© 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. 18902
    Prev
    Next
    INDEX
    Explanations

    rest, interval, break

    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
    äh
    -0.06
    认å®ļ
    -0.06
    enha
    -0.06
    trut
    -0.06
    ahir
    -0.06
    logan
    -0.06
    bez
    -0.06
     INCIDENT
    -0.06
    orso
    -0.06
    intah
    -0.06
    POSITIVE LOGITS
     between
    0.06
    åIJĦæĹı
    0.06
    éĹ´
    0.06
     inter
    0.05
     ais
    0.05
     междÑĥ
    0.05
    æĪĸå¤ļ个
    0.05
     Between
    0.05
    央
    0.05
     zwischen
    0.05
    Activations Density 0.004%

    No Known Activations