© 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. 23-TRANSCODER-HP
    7. 24595
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     about
    -0.34
     “
    -0.31
     P
    -0.31
     single
    -0.30
     åħ³
    -0.30
    âĢ
    -0.29
     size
    -0.28
    åħ³äºİ
    -0.28
    -0.28
     life
    -0.28
    POSITIVE LOGITS
     nostalg
    0.28
    æľĢåıĹ欢è¿İ
    0.26
    ä¼ļä¸Ĭ
    0.26
    å´Ľ
    0.26
    eko
    0.26
    æĮĩåįĹ
    0.26
     Kapoor
    0.26
    åĪºå®¢
    0.26
     incons
    0.25
    band
    0.25
    Activations Density 0.010%

    No Known Activations