© 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. 62753
    Prev
    Next
    INDEX
    Explanations

    fear of

    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
    æĶ¿æ³ķ
    -0.09
    æ®ĭå¿į
    -0.08
    éĵİ
    -0.08
    éĢģ
    -0.08
    çħ²
    -0.08
    æݨ广
    -0.08
    èĩªä¸»
    -0.08
     Ram
    -0.08
    ä¸įä¹ħ
    -0.08
    æ¿Ĥ
    -0.08
    POSITIVE LOGITS
    æģIJæĥ§
    0.33
    害æĢķ
    0.29
    çķıæĥ§
    0.27
     fear
    0.27
    æĥ§
    0.25
    æģIJæħĮ
    0.25
    Fear
    0.25
     Fear
    0.23
    çķı
    0.22
     fears
    0.21
    Activations Density 0.074%

    No Known Activations