© 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. 18736
    Prev
    Next
    INDEX
    Explanations

    comparative adjective

    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
    ä¸ĢåĬ¨
    -0.06
    ä¸ĢåĢĭæľĪ
    -0.05
    act
    -0.05
    otten
    -0.05
    Ĵ
    -0.05
    ä¸Ģ份
    -0.05
    端
    -0.05
    tec
    -0.05
    اک
    -0.05
    riet
    -0.05
    POSITIVE LOGITS
    arily
    0.06
    åħ¶ä»ĸ人çļĦ
    0.06
    ection
    0.06
    elsey
    0.06
    缸è¾ĥ
    0.06
    __.__
    0.06
    quina
    0.06
     avv
    0.06
    >{"
    0.06
    ä»»ä½ķåħ¶ä»ĸ
    0.05
    Activations Density 0.046%

    No Known Activations