© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63635
    Prev
    Next
    INDEX
    Explanations

    German companies and names

    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
    ä¿Ħ
    -0.10
    纶
    -0.09
    ushman
    -0.09
    ái
    -0.09
    .hw
    -0.09
    atcher
    -0.08
    çģµæĦŁ
    -0.08
    éķ¿æ²Ļ
    -0.08
    REATE
    -0.08
    hw
    -0.08
    POSITIVE LOGITS
    å¾·åĽ½
    0.20
     Germany
    0.17
    Germany
    0.16
    ãĥīãĤ¤ãĥĦ
    0.16
     German
    0.15
    æŁıæŀĹ
    0.15
     Germans
    0.14
    German
    0.13
     GmbH
    0.13
    山西çľģ
    0.12
    Activations Density 0.698%

    No Known Activations