© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21220
    Prev
    Next
    INDEX
    Explanations

    German prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IGN
    -0.09
    ilden
    -0.09
    à¹īว
    -0.09
    åĹľ
    -0.09
    qualification
    -0.09
    (filters
    -0.09
    plates
    -0.08
    段
    -0.08
    ç¥ļ
    -0.08
    _tac
    -0.08
    POSITIVE LOGITS
    dater
    0.09
    /interface
    0.08
    éis
    0.08
    ç§
    0.08
    å¡«è¡¥
    0.08
     prominence
    0.08
    lying
    0.08
    rawn
    0.08
    ster
    0.08
    grund
    0.08
    Activations Density 0.018%

    No Known Activations