© 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. 3575
    Prev
    Next
    INDEX
    Explanations

    linear regression and relationships

    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
    åĩºæ±Ĺ
    -0.09
    åıĶåıĶ
    -0.09
    æĹłäºº
    -0.09
    ä¸įèĥ½åĨį
    -0.08
    icum
    -0.08
     likelihood
    -0.08
    赦
    -0.08
    _dll
    -0.08
    quences
    -0.08
    æĹ¥çħ§
    -0.08
    POSITIVE LOGITS
     linear
    0.13
    åħ³ç³»
    0.13
    çĽ´çº¿
    0.11
    .linear
    0.11
    linear
    0.11
     regression
    0.11
     relationship
    0.11
    .Linear
    0.11
    çļĦåħ³ç³»
    0.11
     Linear
    0.10
    Activations Density 0.149%

    No Known Activations