© 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. 32-TRANSCODER-HP
    7. 43608
    Prev
    Next
    INDEX
    Explanations

    article excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geber
    -0.28
     Prop
    -0.28
    Prop
    -0.25
     useStyles
    -0.25
     Manuals
    -0.25
    pecial
    -0.24
     trick
    -0.24
    {}'.
    -0.24
     Bench
    -0.23
    xes
    -0.23
    POSITIVE LOGITS
     rather
    0.34
    åįģåĪĨéĩįè¦ģ
    0.31
    rather
    0.30
    olare
    0.28
     Rather
    0.27
    å¥łå®ļ
    0.27
    Ãłng
    0.26
     quote
    0.25
    æĹłåģ¿
    0.24
    dig
    0.24
    Activations Density 0.002%

    No Known Activations