© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51825
    Prev
    Next
    INDEX
    Explanations

    formulated or formulation

    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
       
    -0.11
    otope
    -0.10
    liness
    -0.09
    listed
    -0.09
    alty
    -0.09
    ç¿Ģ
    -0.09
    åĩ«
    -0.09
    fully
    -0.09
    itters
    -0.09
    .ham
    -0.09
    POSITIVE LOGITS
    IAS
    0.10
    atted
    0.09
    enie
    0.09
    iated
    0.08
    lement
    0.08
     вне
    0.08
    irth
    0.08
    er
    0.08
    anford
    0.08
    æĹ¶éĹ´åĨħ
    0.08
    Activations Density 0.030%

    No Known Activations