© 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. 22632
    Prev
    Next
    INDEX
    Explanations

    else branch continuations

    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
    lina
    -0.07
     intoxic
    -0.06
    estina
    -0.06
    atura
    -0.06
    çĪĨåıijçļĦ
    -0.06
    enca
    -0.06
    红线
    -0.06
    è©IJ
    -0.06
     potr
    -0.06
    rias
    -0.06
    POSITIVE LOGITS
    oy
    0.06
    æ¦Ĥæĭ¬
    0.05
     implied
    0.05
    å®Įæ¯ķ
    0.05
    uku
    0.05
    åĬ¡
    0.05
    allo
    0.05
     Bett
    0.05
     lump
    0.04
     Dial
    0.04
    Activations Density 0.006%

    No Known Activations