© 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. 22095
    Prev
    Next
    INDEX
    Explanations

    register transition

    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
    ä¸ĭæĶ¾
    -0.06
    imte
    -0.06
    stab
    -0.06
    ukas
    -0.06
    esar
    -0.06
    ESS
    -0.06
    asan
    -0.06
    fication
    -0.06
    ´Ī
    -0.06
    αι
    -0.06
    POSITIVE LOGITS
    èĮ¬
    0.05
     fat
    0.05
    诱导
    0.05
     embargo
    0.05
    ibia
    0.05
    isti
    0.05
     depress
    0.05
    æĺ¯ä¸Ģéģĵ
    0.05
    åħĥæ°Ķ
    0.05
    oph
    0.05
    Activations Density 0.001%

    No Known Activations