© 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. 10330
    Prev
    Next
    INDEX
    Explanations

    tools or toolsets

    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
    çģ«éĶħ
    -0.09
    imulator
    -0.09
     Jennings
    -0.09
    ael
    -0.09
    çģı
    -0.08
    èĬĬ
    -0.08
    è¿Ļç§į
    -0.08
    åĨ»
    -0.08
    IAS
    -0.08
    iffin
    -0.08
    POSITIVE LOGITS
    å·¥åħ·
    0.30
     tools
    0.25
     tool
    0.22
    tools
    0.22
     Tools
    0.22
    Tools
    0.20
     Tool
    0.20
     herramient
    0.18
    .tools
    0.18
    tool
    0.17
    Activations Density 0.142%

    No Known Activations