© 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. 2532
    Prev
    Next
    INDEX
    Explanations

    story and parable

    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
    LIN
    -0.08
    åĩĭ
    -0.08
    é¦ĸ
    -0.08
     Cord
    -0.08
    çĶ¥
    -0.08
     dried
    -0.08
    æĵŀ
    -0.08
    _cr
    -0.08
    ollen
    -0.08
    è§ģåĪ°
    -0.08
    POSITIVE LOGITS
    æķħäºĭ
    0.11
    /story
    0.10
     tentang
    0.09
    ç«¥
    0.09
    parable
    0.09
     story
    0.09
    æĶ¿åºľéĩĩè´Ń
    0.09
    ibox
    0.09
    ozo
    0.09
    -story
    0.09
    Activations Density 0.040%

    No Known Activations