© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7469
    Prev
    Next
    INDEX
    Explanations

    household income and budgets

    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
    -0.15
    eus
    -0.11
    plx
    -0.10
    åĩºå¤Ħ
    -0.09
    WAR
    -0.09
    anco
    -0.09
    adic
    -0.09
    fil
    -0.09
    anke
    -0.09
    ata
    -0.09
    POSITIVE LOGITS
    sWith
    0.11
    ily
    0.11
    éªĿ
    0.11
    -scale
    0.11
    ers
    0.10
    -level
    0.10
    çĶ¨åĵģ
    0.10
    ÙĦاÙĨ
    0.10
    sville
    0.09
    еÑģÑĤв
    0.09
    Activations Density 0.009%

    No Known Activations