© 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. 39876
    Prev
    Next
    INDEX
    Explanations

    mental instability or obsession

    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
    èī¯å¿ĥ
    -0.12
    æģ¶
    -0.11
    仡
    -0.10
    æģ¶æĢ§
    -0.09
    éĺŁåijĺ们
    -0.09
    å«ĸ
    -0.09
    AZE
    -0.09
    æģ°
    -0.08
     prep
    -0.08
    iny
    -0.08
    POSITIVE LOGITS
    çĸ¯
    0.11
    å¾ĪæŃ£å¸¸
    0.10
    è¿Ļ个人
    0.10
    æŃ¤äºº
    0.09
    åħ¬åħ±æĸĩåĮĸ
    0.09
    åı£ä¸Ń
    0.09
    çĭĤ
    0.09
    åĹij
    0.09
    çĸ¯çĭĤ
    0.08
    anol
    0.08
    Activations Density 0.033%

    No Known Activations