© 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. 21041
    Prev
    Next
    INDEX
    Explanations

    I + auxiliary or personal statement verbs

    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
    ÙĪات
    -0.07
    urts
    -0.07
    å³°åĢ¼æīŃ磩
    -0.06
    opil
    -0.06
    owns
    -0.06
    filt
    -0.06
    orig
    -0.06
    oves
    -0.06
    animal
    -0.06
    birthdate
    -0.06
    POSITIVE LOGITS
    SI
    0.05
    /out
    0.05
    si
    0.05
    以为æĺ¯
    0.05
     bass
    0.05
    ilik
    0.05
    æ±Ł
    0.05
     ones
    0.05
    éĹ¹
    0.05
    кÑĥп
    0.04
    Activations Density 0.259%

    No Known Activations