© 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. 11093
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or ones

    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
    9
    -0.09
    et
    -0.08
    8
    -0.08
    OOK
    -0.08
    ç¦Ħ
    -0.08
    2
    -0.08
    5
    -0.08
    0
    -0.08
    6
    -0.08
    aN
    -0.07
    POSITIVE LOGITS
     ones
    0.19
     Ones
    0.14
    ones
    0.13
     hers
    0.13
     ours
    0.12
     yours
    0.12
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.11
    .ones
    0.11
    è°Ħ
    0.10
    ãĤĤãģ®ãĤĴ
    0.10
    Activations Density 2.302%

    No Known Activations