© 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. 20227
    Prev
    Next
    INDEX
    Explanations

    when / if followed by certain words

    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
    imp
    -0.06
    ube
    -0.06
    rac
    -0.05
     Loose
    -0.05
    åIJĥåĬĽ
    -0.05
    ándolo
    -0.05
    称
    -0.05
    hee
    -0.05
    稱
    -0.05
     passages
    -0.05
    POSITIVE LOGITS
    ).-
    0.07
    годи
    0.06
    UCH
    0.06
    stal
    0.06
    ):-
    0.06
     emer
    0.06
    ECH
    0.06
    grim
    0.06
    clare
    0.06
    çĩĥ
    0.06
    Activations Density 0.003%

    No Known Activations