© 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. 32600
    Prev
    Next
    INDEX
    Explanations

    banks and banking

    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
    oke
    -0.10
    ä»ĺè´¹
    -0.09
    åŁºåľ°
    -0.09
    .pc
    -0.09
     Ministry
    -0.09
    åı¬
    -0.09
    Guid
    -0.09
    饼
    -0.09
    ä¸Ńéĵģ
    -0.08
     заÑĤ
    -0.08
    POSITIVE LOGITS
     banking
    0.13
     banks
    0.13
    éĵ¶è¡Į
    0.12
    è¡Įéķ¿
    0.12
    éĬĢè¡Į
    0.12
    bank
    0.11
    éĵ¶è¡Įä¸ļ
    0.11
     bank
    0.11
    éĩijèŀįæľºæŀĦ
    0.11
    .bank
    0.11
    Activations Density 0.051%

    No Known Activations