© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57173
    Prev
    Next
    INDEX
    Explanations

    concepts indicating definitions or relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /../
    -0.09
    éments
    -0.08
    pedia
    -0.08
    <|box_end|>
    -0.07
    δο
    -0.07
    ิ
    -0.07
    äºĨäºĭ
    -0.07
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    -0.07
     пожалÑĥйÑģÑĤа
    -0.07
    à¹ģรà¸ģà¸Ĥà¸Ńà¸ĩ
    -0.07
    POSITIVE LOGITS
    à¸Ļà¹Į
    0.07
    uu
    0.07
    allon
    0.06
    OLLOW
    0.06
     (
    0.06
    embra
    0.06
    å§Ĺ
    0.06
    ä¾ĥ
    0.06
    åĬłæĭ¿å¤§
    0.06
    entifier
    0.05
    Activations Density 0.425%

    No Known Activations