© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56753
    Prev
    Next
    INDEX
    Explanations

    nice adjective

    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
    ä¹ĥ
    -0.09
    åĵĪåĵĪ
    -0.09
    äºĺ
    -0.09
    峡
    -0.09
    keys
    -0.09
    éĻī
    -0.09
    å½»
    -0.09
    æ·¹
    -0.09
     Fired
    -0.08
    .mit
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.10
    温馨
    0.09
    稳å®ļçļĦ
    0.09
    cÃŃ
    0.09
    iets
    0.09
    å¹²åĩĢ
    0.09
    -sized
    0.09
    blend
    0.08
    agnost
    0.08
     nice
    0.08
    Activations Density 0.044%

    No Known Activations