© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37155
    Prev
    Next
    INDEX
    Explanations

    possessives followed by ordinals

    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
    让å®ĥ
    -0.09
    mons
    -0.09
    inia
    -0.09
    åħ¬çº¦
    -0.09
    isle
    -0.09
    BITS
    -0.08
    elin
    -0.08
    unts
    -0.08
    å½ĵåį³
    -0.08
    ABA
    -0.08
    POSITIVE LOGITS
    第ä¸ī个
    0.13
    第äºĮ个
    0.11
    第ä¸ī次
    0.11
     third
    0.10
    å¤ļå°ij
    0.10
    èŀĥèŁ¹
    0.09
    åĩłæ¬¡
    0.09
    第
    0.09
    IfExists
    0.09
    è¾ŀ
    0.09
    Activations Density 0.118%

    No Known Activations