© 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. 48084
    Prev
    Next
    INDEX
    Explanations

    Simon + names, places, or titles

    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
    igator
    -0.09
    our
    -0.09
     Gund
    -0.09
    æİĩ
    -0.09
    åĹŀ
    -0.08
    upt
    -0.08
    resh
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
     metam
    -0.08
    uye
    -0.08
    POSITIVE LOGITS
    istic
    0.10
    åĬŀåħ¬åİħ
    0.10
    VERN
    0.10
    æ·±å¤Ħ
    0.10
    nect
    0.10
    etta
    0.09
    ossal
    0.09
    ãģ¦ãĤĤ
    0.09
    UNE
    0.09
    _retry
    0.09
    Activations Density 0.035%

    No Known Activations