© 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. 2121
    Prev
    Next
    INDEX
    Explanations

    colors: red, rose, ribbon

    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
    çķĻç»Ļ
    -0.11
    å°½æĹ©
    -0.09
    客è§Ĥ
    -0.09
    åIJ¹
    -0.09
    èĵ¬
    -0.08
    èŀº
    -0.08
    éĩĩ访
    -0.08
    .mount
    -0.08
    æ±ĩéĽĨ
    -0.08
    çªģåĩº
    -0.08
    POSITIVE LOGITS
    å®ĺ
    0.10
    entic
    0.09
    starter
    0.09
    CardBody
    0.09
     Wel
    0.09
    enger
    0.09
    çĸ¡
    0.09
    æ±´
    0.09
    åĪºå®¢
    0.09
    åı¤åħ¸
    0.08
    Activations Density 0.049%

    No Known Activations