© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51261
    Prev
    Next
    INDEX
    Explanations

    times, vezes, or separate

    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
    eni
    -0.08
    reten
    -0.08
    çĩĥ
    -0.08
    大åĬĽ
    -0.08
    -Day
    -0.08
    lien
    -0.08
    ehler
    -0.08
    owie
    -0.08
    Chain
    -0.08
    IER
    -0.08
    POSITIVE LOGITS
    次æķ°
    0.24
    åĩłæ¬¡
    0.22
    å¤ļ次
    0.20
    两次
    0.19
    ä¸ī次
    0.18
    ä¸Ģ次
    0.18
    æĹłæķ°æ¬¡
    0.16
     twice
    0.15
     Twice
    0.15
    ä¸Ģéģį
    0.15
    Activations Density 0.089%

    No Known Activations