© 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. 112208
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/titles

    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
    äºĨä¸ĭæĿ¥
    -0.24
    çļĦå°±æĺ¯
    -0.23
    è¿Ļä¹Īåģļ
    -0.22
    ax
    -0.22
     fin
    -0.21
    STYLE
    -0.21
     tracked
    -0.20
    umd
    -0.20
    ä¸ĸ
    -0.20
     involved
    -0.20
    POSITIVE LOGITS
    alus
    0.25
    è´©
    0.23
    ROID
    0.23
     fury
    0.22
    ä¸Ģé¡¿
    0.21
    -central
    0.21
    à¹Ģà¸ļ
    0.21
    è¹Ħ
    0.21
     insult
    0.21
    ÑģÑĮ
    0.21
    Activations Density 0.003%

    No Known Activations