© 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. 38547
    Prev
    Next
    INDEX
    Explanations

    diagonal, oblique, slantwise

    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
    åIJł
    -0.09
    è°´
    -0.08
    ersion
    -0.08
    æĬĬå®ĥ
    -0.08
    amp
    -0.08
    enko
    -0.08
    (crate
    -0.08
    (Stack
    -0.08
     Owner
    -0.08
    keeping
    -0.07
    POSITIVE LOGITS
    IENT
    0.11
    éļħ
    0.11
    izable
    0.10
    家çĶ¨
    0.10
    à¸Ħà¸Ńม
    0.10
    èŤ
    0.09
    举æŃ¢
    0.09
    atoi
    0.09
    çºłç¼ł
    0.09
    .Invariant
    0.09
    Activations Density 0.023%

    No Known Activations