© 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. 55606
    Prev
    Next
    INDEX
    Explanations

    plus followed by specific entities

    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
    LAY
    -0.10
    inkel
    -0.09
    ampo
    -0.08
    andes
    -0.08
    ees
    -0.08
    ä¸Ģèĩ´æĢ§
    -0.08
    place
    -0.08
    ase
    -0.08
    places
    -0.08
    eel
    -0.08
    POSITIVE LOGITS
    ieurs
    0.13
    å¤Ń
    0.09
    owed
    0.09
    éĵī
    0.09
    enk
    0.09
    ç½ij绾ç§ijæĬĢ
    0.09
    vo
    0.09
    åİŁæłĩé¢ĺ
    0.09
    åħĪæĬĬ
    0.09
    ì¹ľ
    0.09
    Activations Density 0.019%

    No Known Activations