© 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. 53022
    Prev
    Next
    INDEX
    Explanations

    People with name Harry/Henry

    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
    mile
    -0.27
    å¿į
    -0.27
    åħħåĪĨä½ĵçİ°
    -0.26
    仪表
    -0.26
    èĢIJ
    -0.26
    off
    -0.25
    æĴ
    -0.25
     Gór
    -0.24
    èIJ§
    -0.24
    èĺĸ
    -0.24
    POSITIVE LOGITS
    åģļ大
    0.28
    æĪ¥
    0.26
    prs
    0.25
    ÑıÑī
    0.25
    åĩºåĬ¨
    0.24
    à¸ļร
    0.24
    ÑĥÑİÑī
    0.24
    conditional
    0.24
    åĮºéĹ´
    0.23
    æĿ¥ä¸įåıĬ
    0.23
    Activations Density 0.007%

    No Known Activations