© 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. 61916
    Prev
    Next
    INDEX
    Explanations

    linking to something

    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
    urus
    -0.08
    åŀ
    -0.08
    umen
    -0.08
    æī¿åĬŀ
    -0.08
    çĤ¸
    -0.08
    èĵij
    -0.08
    è´²
    -0.08
    涿
    -0.08
    sole
    -0.08
    æīįèĥ½
    -0.08
    POSITIVE LOGITS
    jt
    0.10
    活泼
    0.09
     linking
    0.09
    æIJ¦
    0.09
    åµĮ
    0.09
    morgan
    0.09
    SSI
    0.09
    _MINUS
    0.08
    æ´»è·ĥ
    0.08
    åħį
    0.08
    Activations Density 0.002%

    No Known Activations