© 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. 56673
    Prev
    Next
    INDEX
    Explanations

    trekking, Star Trek, Trent

    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
    ames
    -0.10
    åħħ足
    -0.09
    iez
    -0.09
    éĻIJæľŁ
    -0.09
    迨
    -0.09
    åĩłçĤ¹
    -0.08
    à¹Īม
    -0.08
    oral
    -0.08
    หมà¸Ķ
    -0.08
     пÑĢоÑģ
    -0.08
    POSITIVE LOGITS
    pping
    0.10
     má»ıi
    0.10
    è¹
    0.10
    sters
    0.09
    shaw
    0.09
    plex
    0.09
    ster
    0.09
    éķ¶
    0.09
    intosh
    0.09
    xin
    0.09
    Activations Density 0.005%

    No Known Activations