© 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. 61497
    Prev
    Next
    INDEX
    Explanations

    TextField numeric

    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
    BuilderFactory
    -0.10
    esak
    -0.09
    è¾»
    -0.09
    Dettagli
    -0.09
    æłĩè¯Ĩçłģ
    -0.08
    CallCheck
    -0.08
    <|box_end|>
    -0.08
    denes
    -0.08
    diri
    -0.08
    utel
    -0.08
    POSITIVE LOGITS
     {@
    0.09
    ↵
    0.09
    '
    0.08
    /
    0.08
    ...
    0.08
    ..
    0.07
    """
    0.07
    '''
    0.06
     dele
    0.06
     */
    0.06
    Activations Density 0.312%

    No Known Activations