© 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. 19791
    Prev
    Next
    INDEX
    Explanations

    influence and daily injustices

    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
    çľ¼çľĭ
    -0.10
    èĥ½æī¾åĪ°
    -0.10
    Interop
    -0.09
    åĨįåĬłä¸Ĭ
    -0.09
     Hank
    -0.08
    çľĭèµ·æĿ¥
    -0.08
    åĬłä¸Ĭ
    -0.08
    _mgmt
    -0.08
    åİ
    -0.08
    ecast
    -0.08
    POSITIVE LOGITS
    æīįæĺ¯çľŁæŃ£
    0.13
    åħ¶å®ŀæĺ¯
    0.11
    è¿Ļæīįæĺ¯
    0.11
    æīįæĺ¯
    0.10
    羣æŃ£çļĦ
    0.10
     actually
    0.10
    åħ¶å¯¦
    0.10
    åħ¶å®ŀå°±æĺ¯
    0.09
    èĩ³åħ³
    0.09
    羣æŃ£
    0.09
    Activations Density 0.135%

    No Known Activations