© 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. 53878
    Prev
    Next
    INDEX
    Explanations

    financing and funding

    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
    æĹ¥å¸¸çĶŁæ´»
    -0.11
    èĤĮ
    -0.10
    讶
    -0.09
    躯
    -0.09
    çĸµ
    -0.09
    bsub
    -0.08
    åĻ¤
    -0.08
    å²Ľä¸Ĭ
    -0.08
    _bases
    -0.08
    åĨ¥
    -0.08
    POSITIVE LOGITS
    èŀįèµĦ
    0.21
    贷款
    0.18
     financing
    0.15
     funding
    0.15
    éĵ¶è¡Į
    0.14
     Funding
    0.14
    èŀį
    0.14
    貸款
    0.14
     banks
    0.13
    èµĦéĩij
    0.13
    Activations Density 0.063%

    No Known Activations