© 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. 49461
    Prev
    Next
    INDEX
    Explanations

    well as

    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
    ãģĿãĤĤãģĿãĤĤ
    -0.11
    ees
    -0.10
    Ñĥм
    -0.10
     them
    -0.10
    ess
    -0.09
     realmente
    -0.09
    è¦ģä¹Ī
    -0.09
    nde
    -0.09
     ấy
    -0.09
    å¦Ĥæŀľè¯´
    -0.09
    POSITIVE LOGITS
    ness
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    -known
    0.10
    ãĤ
    0.09
    born
    0.09
    驾车
    0.09
    åħ¶å®ĥ
    0.09
    è²Į
    0.09
    endra
    0.09
    è·Łå¥¹
    0.09
    Activations Density 0.033%

    No Known Activations