© 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. 31109
    Prev
    Next
    INDEX
    Explanations

    therefore followed by conclusion

    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
    ifier
    -0.12
    ifying
    -0.12
    åĦ¿
    -0.12
    tern
    -0.10
    ieg
    -0.10
    ified
    -0.10
    urb
    -0.10
    -eyed
    -0.10
     ведÑĮ
    -0.10
     zwar
    -0.09
    POSITIVE LOGITS
    forth
    0.12
    说æĺ¯
    0.09
    ocus
    0.09
    ocal
    0.09
    ectors
    0.09
    æĪijæīį
    0.09
    å©¿
    0.09
    asis
    0.09
    ance
    0.09
     motive
    0.08
    Activations Density 0.029%

    No Known Activations