© 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. 50458
    Prev
    Next
    INDEX
    Explanations

    uncle followed by names

    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
    sWith
    -0.09
    ers
    -0.09
    illes
    -0.08
    neau
    -0.08
    aus
    -0.08
    аÑĤелÑĮ
    -0.08
    à¹Į
    -0.08
    åĴĮå®ĮåĸĦ
    -0.08
    åıªè§ģ
    -0.08
    çIJīçĴĥ
    -0.08
    POSITIVE LOGITS
    anness
    0.12
    ject
    0.11
    gram
    0.11
    isplay
    0.10
    urope
    0.10
    hiro
    0.09
     fashioned
    0.09
    appropri
    0.09
    oran
    0.09
    stration
    0.09
    Activations Density 0.005%

    No Known Activations