© 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. 20-TRANSCODER-HP
    7. 130126
    Prev
    Next
    INDEX
    Explanations

    Coding/software updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬłéĩį
    -0.27
    wargs
    -0.25
     Domain
    -0.25
     draining
    -0.25
    ationToken
    -0.24
     ja
    -0.24
    ä¸įå®Į
    -0.24
     Dataset
    -0.24
    æľĽåİ»
    -0.23
    à¹Ģà¸Ł
    -0.23
    POSITIVE LOGITS
     orally
    0.29
    ocl
    0.28
    ths
    0.27
    riad
    0.26
    duc
    0.26
    åĪĨ离
    0.26
    AGR
    0.25
    ells
    0.25
    cona
    0.24
     Portions
    0.24
    Activations Density 0.457%

    No Known Activations