© 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. 56330
    Prev
    Next
    INDEX
    Explanations

    rehearing

    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
    -0.12
    inding
    -0.09
    urator
    -0.08
    oks
    -0.08
    dal
    -0.08
    åį¸
    -0.08
    aceous
    -0.08
    adia
    -0.08
    unist
    -0.08
    ä¿¡ä»°
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģéģį
    0.11
    ä¸Ģéģį
    0.10
    å¤Ķ
    0.10
    moz
    0.09
    大家éĥ½åľ¨
    0.09
    åĬŁè¯¾
    0.09
    wers
    0.09
    æī©åħħ
    0.09
    bate
    0.09
    åİ®
    0.09
    Activations Density 0.006%

    No Known Activations