© 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. 7554
    Prev
    Next
    INDEX
    Explanations

    prefix and suffix components

    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
    leine
    -0.09
    eprom
    -0.09
    گاÙĩ
    -0.08
    äºijä¸Ń
    -0.08
    ewire
    -0.08
    lande
    -0.08
    probe
    -0.08
    caster
    -0.08
    िति
    -0.08
    боÑĢо
    -0.08
    POSITIVE LOGITS
    (
    0.07
    -
    0.07
     (
    0.06
     —
    0.06
     themselves
    0.06
    âĢ
    0.06
     prefix
    0.05
    ehr
    0.05
    0.05
    :
    0.05
    Activations Density 0.437%

    No Known Activations