© 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. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53565
    Prev
    Next
    INDEX
    Explanations

    finance/banking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oggles
    -0.28
     scans
    -0.26
     feats
    -0.26
    (stdin
    -0.26
    ogg
    -0.26
     scanned
    -0.26
     Census
    -0.25
    é£İä¿Ĺ
    -0.25
     capital
    -0.25
    antal
    -0.25
    POSITIVE LOGITS
    å·¥ä¸ļ
    0.29
    家éķ¿ä»¬
    0.26
    社åĮº
    0.26
    åĦĨ
    0.26
    è¾Ħ
    0.26
    åĴķ
    0.25
    年轻人
    0.24
    å·¥æ¥Ń
    0.24
     renters
    0.24
    æĿijæ°ij们
    0.24
    Activations Density 0.014%

    No Known Activations