© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22585
    Prev
    Next
    INDEX
    Explanations

    numbers followed by hyphens or commas

    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
    Negative Logits
    midd
    -0.06
    ست
    -0.06
    iates
    -0.06
    age
    -0.06
    ж
    -0.05
     méd
    -0.05
    rupt
    -0.05
    ï¸İ
    -0.05
     mid
    -0.05
    ned
    -0.05
    POSITIVE LOGITS
    çĦ¶å¤§
    0.06
    åħijç¾İåħĥ
    0.06
    ska
    0.06
    alive
    0.06
     interac
    0.06
    为大家ä»ĭç»į
    0.06
    itia
    0.06
    kÅĤ
    0.06
    atico
    0.06
     LENG
    0.06
    Activations Density 0.006%

    No Known Activations