© 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. 9181
    Prev
    Next
    INDEX
    Explanations

    death and afterlife

    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
    bum
    -0.09
    èĢĹ
    -0.09
     ÑħозÑıй
    -0.09
    å±ģèĤ¡
    -0.09
    没æĶ¶
    -0.08
    nts
    -0.08
    çĬģ
    -0.08
     paranoia
    -0.08
    ä¾Ī
    -0.08
    è°¦
    -0.08
    POSITIVE LOGITS
    å¤©åĽ½
    0.10
    çŀij
    0.10
    unlink
    0.09
    åĪĨæµģ
    0.09
    okay
    0.09
    éĿĴå±±
    0.09
    åİ»äºĨ
    0.09
    äºij端
    0.08
    æ°¸æģĴ
    0.08
     Baltic
    0.08
    Activations Density 0.018%

    No Known Activations