© 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. 18370
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters

    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
    em
    -0.06
    жан
    -0.05
     bre
    -0.05
    å½¹
    -0.05
    egen
    -0.05
    çĶŁ
    -0.05
    emax
    -0.05
    æĬĺ
    -0.05
     Lind
    -0.05
    it
    -0.05
    POSITIVE LOGITS
    åı¯æľĽ
    0.07
    ÅĤow
    0.06
     Peel
    0.06
     оÑĤд
    0.06
    !!.
    0.06
     '".
    0.06
    ãĤ¹ãĥĿ
    0.06
     Trik
    0.06
    ì°°
    0.06
    éļĪ
    0.06
    Activations Density 0.011%

    No Known Activations