© 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. 19077
    Prev
    Next
    INDEX
    Explanations

    west direction or region

    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
    sey
    -0.08
    weiler
    -0.08
    Ñģловно
    -0.08
    /dis
    -0.08
    istic
    -0.08
    stown
    -0.08
    zó
    -0.08
    zana
    -0.08
    zilla
    -0.07
    kla
    -0.07
    POSITIVE LOGITS
    ward
    0.11
    à¹Ģà¸īียà¸ĩ
    0.11
    falen
    0.08
    s
    0.08
    ened
    0.08
    mere
    0.08
    erner
    0.08
    minster
    0.08
    alta
    0.08
    illing
    0.08
    Activations Density 0.079%

    No Known Activations