© 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. 50404
    Prev
    Next
    INDEX
    Explanations

    constant and coefficients

    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
     sebagian
    -0.08
    åĪ©äºļ
    -0.07
    rens
    -0.07
    onse
    -0.07
     заба
    -0.07
    inol
    -0.07
    ÑħодÑĭ
    -0.07
    weis
    -0.07
    被éĢ¼
    -0.07
     Bens
    -0.07
    POSITIVE LOGITS
     constants
    0.10
    ç³»æķ°
    0.09
     coefficient
    0.09
     coefficients
    0.09
    常æķ°
    0.08
     Constants
    0.08
    constants
    0.08
     multiplying
    0.08
     коÑįÑĦÑĦиÑĨи
    0.08
    coeff
    0.08
    Activations Density 0.016%

    No Known Activations