© 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. 17602
    Prev
    Next
    INDEX
    Explanations

    microfilm imaging indexable

    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
    åıijå±ķä¸Ń
    -0.11
    åģļä¸Ģ个
    -0.10
    åī§
    -0.10
    agnar
    -0.10
    _minor
    -0.10
    åĬĩ
    -0.10
    artz
    -0.10
    èĥĮçĿĢ
    -0.10
    zac
    -0.09
    apon
    -0.09
    POSITIVE LOGITS
    1
    0.10
    çļĦè¯Ŀé¢ĺ
    0.09
    2
    0.09
    çĻ»
    0.09
    å½±åĥı
    0.09
    aten
    0.08
    0
    0.08
     fds
    0.08
    5
    0.08
    ewing
    0.08
    Activations Density 0.087%

    No Known Activations