© 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. 8155
    Prev
    Next
    INDEX
    Explanations

    cooking containers

    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
    è§ī
    -0.09
    åħ¬çĦ¶
    -0.09
    qua
    -0.09
    ç«¿
    -0.09
     оÑĤз
    -0.08
    ি
    -0.08
    cean
    -0.08
    ä¸įäºĨ
    -0.08
    odo
    -0.08
     Giov
    -0.08
    POSITIVE LOGITS
    éĩĮçļĦ
    0.10
    积æŀģå¼Ģå±ķ
    0.09
    åĨħçļĦ
    0.09
    orage
    0.09
    arkin
    0.08
    ousse
    0.08
    è¶¾
    0.08
    STALL
    0.08
    积æŀģæİ¨è¿Ľ
    0.08
     Collective
    0.08
    Activations Density 0.025%

    No Known Activations