© 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. 11113
    Prev
    Next
    INDEX
    Explanations

    metallurgical industries and processes

    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
    éĥ¢
    -0.10
    éŀĭåŃIJ
    -0.10
    modx
    -0.09
    å¿į
    -0.09
    OLF
    -0.09
    ÅĽcie
    -0.08
    主管éĥ¨éŨ
    -0.08
    å·«
    -0.08
    OfClass
    -0.08
    éħ¿
    -0.08
    POSITIVE LOGITS
    inator
    0.10
    åĨįéĢł
    0.09
    egin
    0.08
    åİĤ
    0.08
    bek
    0.08
    åĨ¶éĩij
    0.08
    åĹ£
    0.08
    æĬĬèĩªå·±
    0.08
    ering
    0.08
    еÑĩ
    0.07
    Activations Density 0.046%

    No Known Activations