© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33818
    Prev
    Next
    INDEX
    Explanations

    boolean values or placeholders

    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
    hadap
    -0.08
    artos
    -0.07
    à¸ģà¸ģ
    -0.07
    empla
    -0.07
    è¿ĩå¾Ĺ
    -0.07
    hun
    -0.07
    /fw
    -0.07
    iach
    -0.07
    imbabwe
    -0.07
    ppe
    -0.07
    POSITIVE LOGITS
    禺
    0.08
    ely
    0.07
    incer
    0.07
    大ä¸Ī夫
    0.07
    ahi
    0.07
    åīĶéĢı
    0.06
    è¿ĻæĹłçĸij
    0.06
    ottom
    0.06
    oci
    0.06
    essor
    0.06
    Activations Density 0.014%

    No Known Activations