© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6187
    Prev
    Next
    INDEX
    Explanations

    Names of things/organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adjusted
    -0.28
    Adjusted
    -0.26
    adjusted
    -0.25
     Calling
    -0.25
    PRI
    -0.25
    eday
    -0.24
    adjust
    -0.24
     admitted
    -0.24
     adjust
    -0.23
     ranged
    -0.23
    POSITIVE LOGITS
     pet
    0.28
    å°Ĩ以
    0.26
    á»Ĭ
    0.24
     poll
    0.24
    storm
    0.24
    è£ľ
    0.24
     Orr
    0.23
    fds
    0.23
     fld
    0.23
    Orm
    0.23
    Activations Density 0.044%

    No Known Activations