© 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. 56297
    Prev
    Next
    INDEX
    Explanations

    adrenaline and renal

    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
    roe
    -0.10
    ings
    -0.09
    åīį线
    -0.09
    é¡¿
    -0.09
    ett
    -0.09
    ening
    -0.08
    _fa
    -0.08
    isci
    -0.08
    etro
    -0.08
    vak
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.10
    åħħæ²Ľ
    0.10
    èĺĸ
    0.10
    åī¯å±Ģéķ¿
    0.10
    hir
    0.09
    å±Ģåī¯å±Ģéķ¿
    0.09
    åį¿
    0.09
    æīĭ
    0.09
    onis
    0.09
    èĶ·
    0.09
    Activations Density 0.032%

    No Known Activations