© 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. 18265
    Prev
    Next
    INDEX
    Explanations

    phrasing or repositioning

    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
    а
    -0.07
    üz
    -0.06
    late
    -0.06
    uel
    -0.05
    e
    -0.05
    ant
    -0.05
     distributed
    -0.05
    distributed
    -0.05
     Forget
    -0.05
    ab
    -0.05
    POSITIVE LOGITS
    manship
    0.07
    æѤçĶŁ
    0.07
    åĭĿè²ł
    0.07
    بÙĪر
    0.07
    suming
    0.07
     showc
    0.06
    kelse
    0.06
    velopp
    0.06
    lables
    0.06
    تÙĬ
    0.06
    Activations Density 0.001%

    No Known Activations