© 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. 38667
    Prev
    Next
    INDEX
    Explanations

    IP, RTC, phony, calls, telephony

    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¯
    -0.09
    vice
    -0.09
    èį¯ä¸ļ
    -0.09
    é«ĺä»·
    -0.08
    heiten
    -0.08
    液åİĭ
    -0.08
    çĤŃ
    -0.08
    nip
    -0.08
    andes
    -0.08
    hood
    -0.08
    POSITIVE LOGITS
    éĢģæĿ¥
    0.08
    æİĤ
    0.08
    æĵİ
    0.08
    ãĤ¹ãĥĿãĥĥãĥĪ
    0.08
    eras
    0.08
    ä¹ħäºĨ
    0.08
    çĶ·çĶŁ
    0.08
    athon
    0.08
    (Packet
    0.08
    åIJģ
    0.08
    Activations Density 0.006%

    No Known Activations