© 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. 27270
    Prev
    Next
    INDEX
    Explanations

    stereoscopic, stereotype, steroid

    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
    urator
    -0.11
    stay
    -0.09
    erty
    -0.09
    sie
    -0.09
    nish
    -0.09
    nen
    -0.09
    urations
    -0.08
    ired
    -0.08
    uation
    -0.08
    sel
    -0.08
    POSITIVE LOGITS
    åĮĸçļĦ
    0.11
    ONUS
    0.10
    ç¬Ĩ
    0.10
    halb
    0.10
    wart
    0.10
    iou
    0.09
    afil
    0.09
    ubbles
    0.09
    ategy
    0.09
     här
    0.09
    Activations Density 0.046%

    No Known Activations