© 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. 51045
    Prev
    Next
    INDEX
    Explanations

    hinge, pivotal, articulated connections

    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
    oothing
    -0.09
    aceous
    -0.09
    tempts
    -0.09
     вз
    -0.09
    èĺħ
    -0.09
    çļĦ游æĪı
    -0.08
    çĹĺ
    -0.08
    ä¹Łä¸º
    -0.08
    åģ¿
    -0.08
    _hierarchy
    -0.08
    POSITIVE LOGITS
    edList
    0.12
    ues
    0.10
    å¤Ħ
    0.10
    åľ°å¸¦
    0.09
    panic
    0.09
    ered
    0.09
    UES
    0.09
    ESCO
    0.09
    áĥĻ
    0.09
    _PAD
    0.09
    Activations Density 0.168%

    No Known Activations