© 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. 18144
    Prev
    Next
    INDEX
    Explanations

    other

    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
    çĽ²
    -0.10
    ä¸į便
    -0.09
    翳
    -0.09
    upt
    -0.09
    缴éĶĢ
    -0.08
    /mp
    -0.08
    æĹłå½¢
    -0.08
    upo
    -0.08
    å°ĸ
    -0.08
    éĤµ
    -0.08
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.13
    åħ¶ä»ĸçļĦ
    0.12
    åħ¶å®ĥ
    0.11
    次è¦ģ
    0.11
    .other
    0.11
    åħ¶ä½Ļ
    0.10
     smaller
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
     other
    0.10
    æĪĸå¤ļæĪĸå°ij
    0.10
    Activations Density 0.176%

    No Known Activations