© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52648
    Prev
    Next
    INDEX
    Explanations

    technology corporations and company 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
    åĥı个
    -0.11
    åĿļæŀľ
    -0.09
    å¤Ļ
    -0.09
    åłij
    -0.09
    Ñĥв
    -0.09
    inion
    -0.08
    óc
    -0.08
    çľ·
    -0.08
    bote
    -0.08
    obar
    -0.08
    POSITIVE LOGITS
    åħ¬åı¸çļĦ
    0.13
    åħ¬åı¸
    0.13
     corporation
    0.12
    è¿Ļ家åħ¬åı¸
    0.12
     company
    0.11
     Corporation
    0.10
    äºĨèĩªå·±çļĦ
    0.10
     Company
    0.10
    company
    0.10
    åĪ¶éĢł
    0.09
    Activations Density 0.224%

    No Known Activations