© 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. 21773
    Prev
    Next
    INDEX
    Explanations

    python string methods

    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
    å§Ķ
    -0.06
    elp
    -0.05
    cone
    -0.05
    ilis
    -0.05
    å»ī
    -0.05
    è·¯
    -0.05
    ảy
    -0.05
    æ¶Ī
    -0.05
    .service
    -0.05
    ascal
    -0.05
    POSITIVE LOGITS
    æĬ±èijĹ
    0.06
    è¶ĭ
    0.05
    åľ¨çĽ®åīį
    0.05
    iable
    0.05
    رض
    0.05
    åı½
    0.05
    次第
    0.05
     Banca
    0.05
    æĹłåħ¬å®³
    0.05
    oggio
    0.05
    Activations Density 0.105%

    No Known Activations