© 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. 19955
    Prev
    Next
    INDEX
    Explanations

    will verb followed by action

    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
     potentially
    -0.07
    possibly
    -0.06
     undoubtedly
    -0.05
     Possibly
    -0.05
    ::-
    -0.05
     arguably
    -0.05
     possibly
    -0.05
    dez
    -0.05
    pot
    -0.05
     guaranteed
    -0.05
    POSITIVE LOGITS
     Enough
    0.08
    Enough
    0.08
     enough
    0.08
     genug
    0.07
    ืà¸Ń
    0.07
    atson
    0.07
    çľ¯çľ¯
    0.07
    è¶³å¤Ł
    0.06
    è¶³å¤ł
    0.06
    åĨĮ
    0.06
    Activations Density 0.033%

    No Known Activations