© 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. 2411
    Prev
    Next
    INDEX
    Explanations

    following example

    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
    rocessing
    -0.09
    rach
    -0.08
     Called
    -0.08
    éĻĮ
    -0.08
    çľĭæĿ¥
    -0.07
    alak
    -0.07
    olos
    -0.07
    naissance
    -0.07
    egie
    -0.07
    athan
    -0.07
    POSITIVE LOGITS
    æľī以ä¸ĭ
    0.08
    }):
    0.07
    abus
    0.06
    ÑĢÑĥÑĤ
    0.06
    åħ·æľī以ä¸ĭ
    0.06
    ,%
    0.06
     voici
    0.06
    以ä¸ĭåĩł
    0.06
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.06
     lautet
    0.06
    Activations Density 0.450%

    No Known Activations