© 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. 22-TRANSCODER-HP
    7. 87706
    Prev
    Next
    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     definition
    -0.81
    å®ļä¹ī
    -0.79
     Definition
    -0.74
     definitions
    -0.73
    Definition
    -0.68
     defined
    -0.68
     define
    -0.66
    definition
    -0.65
    _definition
    -0.60
    define
    -0.58
    POSITIVE LOGITS
     Floyd
    0.28
    ä¹ĭåĬ¿
    0.27
    è¿Ļåıª
    0.26
    -fly
    0.26
    樱æ¡ĥ
    0.25
    à¤Ŀ
    0.25
    æĺ¶
    0.25
    oire
    0.25
    клÑİÑĩи
    0.24
    -decoration
    0.24
    Activations Density 0.001%

    No Known Activations