© 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. 1151
    Prev
    Next
    INDEX
    Explanations

    craters, sinkholes, pits

    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
    缯
    -0.11
    åīª
    -0.10
    沿线
    -0.09
    igid
    -0.09
    ãģ§ãģĤ
    -0.09
    ìĤ¬íķŃ
    -0.09
    ÑıÑħ
    -0.08
    çŃ¾
    -0.08
    Cors
    -0.08
    åIJĪæ³ķ
    -0.08
    POSITIVE LOGITS
     Pit
    0.10
    åĿij
    0.10
    屿
    0.10
     rims
    0.09
     rim
    0.09
     pit
    0.09
    .consume
    0.09
    éĶħ
    0.09
     Concord
    0.09
    çĬ¶
    0.09
    Activations Density 0.102%

    No Known Activations