© 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. 31167
    Prev
    Next
    INDEX
    Explanations

    built by, operated by, directed by

    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
    ðŁ¤·
    -0.10
    UEL
    -0.10
    AYS
    -0.10
    .IsNullOr
    -0.09
    onte
    -0.09
    ENTE
    -0.09
    /cards
    -0.09
    åĪ»
    -0.09
     вÑģÑĤÑĢ
    -0.09
    ведениÑı
    -0.09
    POSITIVE LOGITS
    èĨ³
    0.10
    ES
    0.09
    äºĨä¸Ģæī¹
    0.09
     Able
    0.09
    ç»Ŀ大å¤ļæķ°
    0.08
    most
    0.08
    2
    0.08
     quite
    0.08
    èĩªè§ī
    0.08
    大çĪ·
    0.08
    Activations Density 0.082%

    No Known Activations