© 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. 55298
    Prev
    Next
    INDEX
    Explanations

    numbers followed by `]` or `}`

    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
    åıijå¸ĥä¿¡æģ¯
    -0.07
    alas
    -0.06
    äºļçī¹
    -0.06
    cif
    -0.06
    翼翼
    -0.06
    wide
    -0.06
    _basis
    -0.06
    çī¹
    -0.06
     widened
    -0.06
    arity
    -0.06
    POSITIVE LOGITS
    -et
    0.07
    Ù°
    0.07
    大åıĶ
    0.07
    ä¸Ńåħ¬
    0.07
    èĩªé¦ĸ
    0.07
    åħ¶ä»ĸ类似éĹ®é¢ĺ
    0.06
    è°£
    0.06
    дзе
    0.06
    @example
    0.06
    声åIJį
    0.06
    Activations Density 0.012%

    No Known Activations