© 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. 21054
    Prev
    Next
    INDEX
    Explanations

    sample size notation (n=)

    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
    bidden
    -0.06
    geld
    -0.06
    adge
    -0.06
    Äĺ
    -0.06
    adrat
    -0.06
    Äħdu
    -0.06
    ÄĦ
    -0.06
     RELA
    -0.06
    Äħd
    -0.06
    cesi
    -0.06
    POSITIVE LOGITS
     -
    0.06
    å°¤åħ¶æĺ¯
    0.05
    upa
    0.05
    对åIJĦ
    0.05
    еÑĢе
    0.05
    çĬ¯
    0.05
    lab
    0.05
    éĭŃ
    0.05
    toa
    0.05
    lag
    0.05
    Activations Density 0.024%

    No Known Activations