© 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. 22617
    Prev
    Next
    INDEX
    Explanations

    cause or enable events

    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
    irs
    -0.10
    ukan
    -0.09
    说æĪij
    -0.09
    æ·±çŁ¥
    -0.09
    (ls
    -0.09
    ony
    -0.09
    为äºĨ让
    -0.09
    ÙĪÙĨØ©
    -0.08
    race
    -0.08
    以åħ¶
    -0.08
    POSITIVE LOGITS
     us
    0.11
    åĪ«äºº
    0.11
    人们
    0.10
     him
    0.10
     it
    0.09
     them
    0.09
    å®ĥ
    0.08
    人们对
    0.08
    æĩ¦
    0.08
     to
    0.08
    Activations Density 0.159%

    No Known Activations