© 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. 22969
    Prev
    Next
    INDEX
    Explanations

    your purpose or goals

    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
    ä¸įå°ij
    -0.10
    ERIC
    -0.10
    ogens
    -0.09
     акÑĤÑĥ
    -0.09
    çŃ
    -0.09
    éĩĬ
    -0.09
    éĢıè§Ĩ
    -0.09
    æĪijåıijçİ°
    -0.09
    ILA
    -0.09
    åĶ¯
    -0.08
    POSITIVE LOGITS
     desired
    0.12
     desires
    0.09
    缮æłĩ
    0.09
    desired
    0.09
     budget
    0.09
    è§Ħ模æľĢ大
    0.09
    åĩŃä»Ģä¹Ī
    0.09
     benöt
    0.09
    æĥ³æī¾
    0.09
     Desired
    0.08
    Activations Density 0.202%

    No Known Activations