© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18950
    Prev
    Next
    INDEX
    Explanations

    file input/output

    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
    adership
    -0.06
    Ùĩ
    -0.05
    yce
    -0.05
    第ä¸Ģ人
    -0.05
     verst
    -0.05
    edig
    -0.05
    imated
    -0.05
    .twitter
    -0.05
    ä½ĵèĤ²éĶ»çĤ¼
    -0.05
     Stars
    -0.05
    POSITIVE LOGITS
    ible
    0.06
    —a
    0.06
    azi
    0.06
    ç²Ĺçķ¥
    0.05
    ential
    0.05
    æĺĩ
    0.05
    çĺ¸
    0.05
    alti
    0.05
    æħ§
    0.05
    frey
    0.05
    Activations Density 0.004%

    No Known Activations