© 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. 21745
    Prev
    Next
    INDEX
    Explanations

    pronoun or name followed by a verb

    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
    ...
    -0.06
    âĢ¦
    -0.06
    h
    -0.06
    p
    -0.05
    hd
    -0.05
    'd
    -0.05
    ого
    -0.05
    ’d
    -0.05
    odge
    -0.05
    Âł
    -0.04
    POSITIVE LOGITS
     **:**
    0.08
    -found
    0.07
    ttore
    0.07
    undur
    0.07
    è¿Ļåı«
    0.07
    intérêt
    0.07
     fairly
    0.06
    aira
    0.06
    rets
    0.06
    ["$
    0.06
    Activations Density 0.033%

    No Known Activations