© 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. 10303
    Prev
    Next
    INDEX
    Explanations

    necessary, needed, or required with specifications

    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
    ohn
    -0.10
    æĿ¥çĶµ
    -0.10
    æ¯ıä¸Ģä½į
    -0.10
    _fds
    -0.10
    大åħ¨
    -0.09
    QUAL
    -0.09
    å®ļäºĨ
    -0.09
    æĺİæĹ¥
    -0.09
    éĺ½
    -0.09
    веÑĩ
    -0.09
    POSITIVE LOGITS
    å¿ħè¦ģçļĦ
    0.30
     necessary
    0.26
    necessary
    0.22
    å¿ħè¦ģ
    0.21
     необÑħодим
    0.20
     needed
    0.20
    å¿ħè¦ģãģª
    0.19
     required
    0.19
    æīĢéľĢçļĦ
    0.18
    åºĶæľīçļĦ
    0.18
    Activations Density 0.106%

    No Known Activations