© 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. 7650
    Prev
    Next
    INDEX
    Explanations

    houses and related words

    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
    uzzi
    -0.10
    antic
    -0.09
    ï¸İ
    -0.08
    ãģĺãĤĵ
    -0.08
    ães
    -0.08
    ients
    -0.08
    ÑĪе
    -0.08
    ש×Ķ
    -0.07
    ity
    -0.07
    ت
    -0.07
    POSITIVE LOGITS
    mates
    0.10
    ings
    0.10
    keeping
    0.09
    hood
    0.09
    er
    0.08
    elling
    0.08
    aight
    0.08
    holder
    0.08
    ette
    0.08
    erlo
    0.08
    Activations Density 0.039%

    No Known Activations