© 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. 20628
    Prev
    Next
    INDEX
    Explanations

    initialization and prior states

    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
     Exclusive
    -0.07
    åĩıè´Ł
    -0.07
     eksklus
    -0.06
    ìĿ´íĦ°
    -0.06
    åIJ¸
    -0.06
     cumul
    -0.06
    áy
    -0.06
    ç½ĹéĤ£
    -0.06
    Exclusive
    -0.06
     Exclus
    -0.06
    POSITIVE LOGITS
     guesses
    0.07
     guess
    0.07
     Guess
    0.06
    çĮľæµĭ
    0.06
     guessing
    0.06
    guess
    0.06
    Âł
    0.06
    Guess
    0.06
    _guess
    0.06
    èįī
    0.05
    Activations Density 0.008%

    No Known Activations