© 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. 38934
    Prev
    Next
    INDEX
    Explanations

    chain / chain-link / chain-free / chaining

    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
    æĹĮ
    -0.09
     ТÑĥÑĢ
    -0.09
     Sims
    -0.09
    èĢĦ
    -0.08
     Hind
    -0.08
    ylene
    -0.08
    ÑĩеÑĢ
    -0.08
    亡
    -0.08
    å¸ĤæķĻèĤ²
    -0.08
    åľŁèĢ³åħ¶
    -0.08
    POSITIVE LOGITS
    éĵ¾
    0.24
     chain
    0.23
     Chain
    0.22
    (chain
    0.22
    -chain
    0.21
    éĵ¾æĿ¡
    0.20
    chain
    0.20
    .chain
    0.19
    Chain
    0.19
    CHAIN
    0.19
    Activations Density 0.199%

    No Known Activations