© 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. 33183
    Prev
    Next
    INDEX
    Explanations

    mountain tops

    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
    Gab
    -0.10
     Gabri
    -0.09
     gab
    -0.09
    ilter
    -0.09
    é²Ī
    -0.09
    åħ¬å¼Ģ课
    -0.08
    éĶ²
    -0.08
    沪深
    -0.08
    åįĥåı¤
    -0.08
    iverse
    -0.08
    POSITIVE LOGITS
     ÑĢÑıдом
    0.09
    allas
    0.08
    htable
    0.08
    åĨ¶
    0.08
     miscellaneous
    0.08
    /close
    0.08
    nod
    0.08
    è¿İæİ¥
    0.08
     PRES
    0.08
    /connect
    0.08
    Activations Density 0.035%

    No Known Activations