© 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. 4683
    Prev
    Next
    INDEX
    Explanations

    learners and related 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
    gear
    -0.09
    çĶ¨äºº
    -0.08
    geme
    -0.08
    审åĪ¤
    -0.08
    own
    -0.08
    å±ĭéĩĮ
    -0.08
    ÙĪاÙĨ
    -0.08
    ford
    -0.08
    born
    -0.08
    иÑĢован
    -0.08
    POSITIVE LOGITS
    rough
    0.10
    hips
    0.10
    innen
    0.10
    пи
    0.10
    æĺĶ
    0.10
    IPP
    0.09
    soever
    0.09
    hani
    0.08
    åIJĪä¸Ģ
    0.08
    zelf
    0.08
    Activations Density 0.010%

    No Known Activations