© 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. 17256
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and titles

    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
    isci
    -0.05
     UND
    -0.05
     +(
    -0.05
    饮
    -0.05
    اÙĪر
    -0.05
    ainer
    -0.05
    软
    -0.05
    çĶ¨äºİ
    -0.05
    硬
    -0.05
    éłĺåŁŁ
    -0.05
    POSITIVE LOGITS
    pire
    0.06
    antes
    0.06
    пл
    0.06
    pton
    0.06
    onné
    0.05
     bel
    0.05
    èĭĹæľ¨
    0.05
     Õ¢
    0.05
    ä¸įåı¯æĢķ
    0.05
    ritten
    0.05
    Activations Density 0.005%

    No Known Activations