© 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. 18044
    Prev
    Next
    INDEX
    Explanations

    possessive nouns or articles

    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
     диÑģкомÑĦоÑĢ
    -0.07
    clist
    -0.07
    飯
    -0.06
    asel
    -0.06
    brands
    -0.06
    istle
    -0.06
    URRE
    -0.06
    istel
    -0.06
    Į¨
    -0.06
    åİĭåĬĽå¤§
    -0.06
    POSITIVE LOGITS
     off
    0.05
    ément
    0.05
     entirely
    0.05
    ²
    0.05
    off
    0.05
    常è§ģçļĦ
    0.05
    å®Įåħ¨
    0.05
     finances
    0.05
    å±ŀäºİ
    0.05
    arian
    0.04
    Activations Density 0.004%

    No Known Activations