© 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. 36167
    Prev
    Next
    INDEX
    Explanations

    divine beings / supernatural agents

    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
    isser
    -0.10
    è¿Ļè¾¹
    -0.09
    lose
    -0.09
    ói
    -0.09
    åıįæŃ£
    -0.09
    cord
    -0.08
    Ñĩин
    -0.08
    lse
    -0.08
    çĶŁæĦı
    -0.08
    åĵįèµ·
    -0.08
    POSITIVE LOGITS
     اÙĦرØŃ
    0.09
    æĬµ
    0.08
    aky
    0.08
    帮åĬ©
    0.08
    们çļĦ
    0.08
    Nm
    0.08
    prech
    0.08
    ftware
    0.08
    ucker
    0.08
    uzzi
    0.08
    Activations Density 0.039%

    No Known Activations