© 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. 7144
    Prev
    Next
    INDEX
    Explanations

    cutting or slicing action

    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
    å°Ħ
    -0.10
    çĶ¨åľ°
    -0.09
    cÃŃ
    -0.09
    _PUSH
    -0.09
    ytic
    -0.09
     resh
    -0.08
    queeze
    -0.08
    idal
    -0.08
    enville
    -0.08
    å¡ijéĢł
    -0.08
    POSITIVE LOGITS
    å®ŀçĶ¨æĢ§
    0.09
    平衡
    0.09
    éĶĻäºĨ
    0.09
    èij³
    0.09
    ä¸į认è¯Ĩ
    0.08
     invitation
    0.08
     DISP
    0.08
    èĥ½æĬĬ
    0.08
    éĻį
    0.08
    缴åįĩ
    0.08
    Activations Density 0.087%

    No Known Activations