© 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. 56365
    Prev
    Next
    INDEX
    Explanations

    anc/ant/and words

    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
    ally
    -0.11
    lier
    -0.11
    庵
    -0.11
    ends
    -0.10
    wards
    -0.10
    岸
    -0.10
    ected
    -0.10
    anford
    -0.10
    antis
    -0.09
    ting
    -0.09
    POSITIVE LOGITS
    forth
    0.16
    /or
    0.14
    /OR
    0.13
    aroo
    0.11
    lı
    0.11
     dolayı
    0.10
    ın
    0.10
    alyzed
    0.10
    ieri
    0.10
    涸
    0.10
    Activations Density 0.186%

    No Known Activations