© 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. 39449
    Prev
    Next
    INDEX
    Explanations

    business or organizational aspects

    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
    occhi
    -0.08
    orden
    -0.07
    "—
    -0.07
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.06
    å¸Ń
    -0.06
    è¯Ń
    -0.06
    éĽį
    -0.06
    icÃŃ
    -0.06
    èĩ£
    -0.06
    UP
    -0.06
    POSITIVE LOGITS
    éĥ½èĥ½å¤Ł
    0.08
    aries
    0.08
    usses
    0.08
    æĸ°è§Ħå®ļ
    0.07
    eldo
    0.07
    VEST
    0.07
    iega
    0.07
    ене
    0.07
    è¿ĺèĥ½å¤Ł
    0.07
    ÑĤеÑĢе
    0.07
    Activations Density 0.013%

    No Known Activations