© 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. 38653
    Prev
    Next
    INDEX
    Explanations

    affidavit, certificate, signed, self

    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
     germ
    -0.11
     Germ
    -0.10
    汩
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    .metamodel
    -0.08
    .NULL
    -0.08
    大åİħ
    -0.08
    ниÑĩ
    -0.08
    驳
    -0.08
    coat
    -0.08
    POSITIVE LOGITS
     affidavit
    0.10
     attest
    0.10
    çŃ¾åIJį
    0.10
    主è§Ĥ
    0.09
    对ä¼ģä¸ļ
    0.09
    çŃ¾åŃĹ
    0.09
    认è¯ģ
    0.09
    åĩŃ
    0.09
    声æĺİ
    0.09
    æĢĿ念
    0.09
    Activations Density 0.040%

    No Known Activations