© 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. 7810
    Prev
    Next
    INDEX
    Explanations

    survey methods

    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
    æĹĥ
    -0.09
    å®ŀä¾ĭ
    -0.09
    ä¸ŃéĹ´
    -0.08
    itr
    -0.08
    ActionCreators
    -0.08
    mentor
    -0.08
    éĩijå±±
    -0.08
    _VF
    -0.08
    het
    -0.08
    èĮĤ
    -0.08
    POSITIVE LOGITS
    åıĹ访èĢħ
    0.13
    æĶ¶éĽĨ
    0.13
    éĹ®åį·
    0.13
    collector
    0.12
    å¿ĥçIJĨåѦ
    0.12
     collecting
    0.11
    éĩĩéĽĨ
    0.11
    çłĶ究æĪIJæŀľ
    0.11
    æIJľéĽĨ
    0.10
    å¾ģéĽĨ
    0.10
    Activations Density 0.252%

    No Known Activations