© 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. 64623
    Prev
    Next
    INDEX
    Explanations

    toward or towards

    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
    atak
    -0.09
    á»ħ
    -0.09
    nik
    -0.08
    æĹĹé¼ĵ
    -0.08
    åĺĺ
    -0.08
    empre
    -0.08
    ástico
    -0.08
    èij©
    -0.08
    å¾·åįİ
    -0.07
    åĩºæ²¡
    -0.07
    POSITIVE LOGITS
     toward
    0.11
     towards
    0.10
     menuju
    0.10
     achieving
    0.09
     better
    0.09
     deeper
    0.09
    å®ŀçİ°
    0.08
     achieve
    0.08
    Towards
    0.08
    æĹ©æĹ¥
    0.08
    Activations Density 0.325%

    No Known Activations