© 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. 61337
    Prev
    Next
    INDEX
    Explanations

    changed, improved, reduced

    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
    绪
    -0.08
    รร
    -0.07
    _truth
    -0.07
    éľ²æ°´
    -0.07
    enca
    -0.07
    ç´«èĸĩ
    -0.06
    opup
    -0.06
    èĪĴå¿ĥ
    -0.06
    .lo
    -0.06
    vor
    -0.06
    POSITIVE LOGITS
    äºĨçļĦ
    0.07
    ÙĦاØŃ
    0.07
     drast
    0.07
    ovski
    0.07
    à¹Ģà¸ļ
    0.07
     drastic
    0.07
    eges
    0.07
    åIJİæľī
    0.07
    ÑĢÑıз
    0.07
     ÙĤÙĦÙĬ
    0.06
    Activations Density 0.478%

    No Known Activations