© 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. 20784
    Prev
    Next
    INDEX
    Explanations

    source, gain, community, lifetime, shadow, presents

    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
    å°¤
    -0.07
    ubs
    -0.07
    elan
    -0.07
     inca
    -0.06
    _REQUIRED
    -0.06
    ÅĤad
    -0.06
    еÑĢб
    -0.06
     Renzi
    -0.06
     radiant
    -0.06
    èĩªå¤ĩ
    -0.06
    POSITIVE LOGITS
    ccione
    0.08
    ĤŃ
    0.08
    è
    0.07
    褶
    0.07
    (pipe
    0.07
    åĬĽå£«
    0.07
     popr
    0.07
    yre
    0.07
    Callbacks
    0.07
     Fold
    0.07
    Activations Density 0.001%

    No Known Activations