© 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. 4435
    Prev
    Next
    INDEX
    Explanations

    instructions and recommendations

    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
    tainment
    -0.09
    cobra
    -0.09
    isu
    -0.09
    atings
    -0.09
    acional
    -0.09
    POSITE
    -0.08
    èĶĶ
    -0.08
    configs
    -0.08
    çĿĽ
    -0.08
    åĬłæĭī
    -0.08
    POSITIVE LOGITS
     yourself
    0.07
    0.06
    å¿ħè¦ģæŶ
    0.06
     good
    0.06
     Mr
    0.06
     otherwise
    0.06
    /
    0.06
     exact
    0.06
    åºĶæľī
    0.05
    *
    0.05
    Activations Density 0.015%

    No Known Activations