© 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. 16876
    Prev
    Next
    INDEX
    Explanations

    listing examples or options

    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
    线ä¸Ĭ线
    -0.07
     anytime
    -0.07
     even
    -0.06
    kannya
    -0.06
    ven
    -0.06
    inkl
    -0.06
    anyak
    -0.06
     increÃŃ
    -0.06
    èĶ
    -0.06
     anche
    -0.06
    POSITIVE LOGITS
    ly
    0.07
    atically
    0.06
    ain
    0.06
    ewe
    0.05
    ambda
    0.05
    aily
    0.05
    act
    0.05
    ubo
    0.05
    æłĩåĩĨ
    0.04
    is
    0.04
    Activations Density 0.010%

    No Known Activations