© 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. 30553
    Prev
    Next
    INDEX
    Explanations

    consulting firm

    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
    æĴ·
    -0.08
    è½½
    -0.08
    继
    -0.08
    éºĿ
    -0.08
    DOC
    -0.08
    çİĩåħĪ
    -0.08
    ãĥīãĥ«
    -0.08
    çªģåıij
    -0.08
    rig
    -0.08
     DOC
    -0.08
    POSITIVE LOGITS
    åĴ¨è¯¢æľįåĬ¡
    0.16
    顾éĹ®
    0.15
     consulting
    0.14
     Consulting
    0.14
    åĴ¨è¯¢
    0.14
     consultants
    0.13
    컨
    0.12
     consultancy
    0.12
    帮åĬ©ä¼ģä¸ļ
    0.12
     consultant
    0.11
    Activations Density 0.122%

    No Known Activations