© 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. 3085
    Prev
    Next
    INDEX
    Explanations

    like and know

    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
    !.
    -0.08
    !,
    -0.07
    !\
    -0.07
    !",
    -0.07
    ãģ§ãģ¯ãģĤãĤĬãģ¾ãģĽãĤĵ
    -0.07
    åīįå¾Ģ
    -0.07
    ![
    -0.07
    !).
    -0.07
     awaiting
    -0.07
    POSITIVE LOGITS
     kinda
    0.13
     thing
    0.12
    çļĦéĤ£ç§į
    0.11
     stuff
    0.11
     things
    0.10
    éĤ£ç§į
    0.10
     gitu
    0.10
     basically
    0.10
     yeah
    0.10
    没åķ¥
    0.09
    Activations Density 1.054%

    No Known Activations