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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5174
    Prev
    Next
    INDEX
    Explanations

    related

    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
     cornerstone
    -0.24
    anton
    -0.24
    LinkId
    -0.23
    -corner
    -0.23
     Redistributions
    -0.23
    ণ
    -0.22
     Impress
    -0.22
    ottom
    -0.22
    åħ·
    -0.22
     corner
    -0.22
    POSITIVE LOGITS
    äºİæѤ
    0.33
    ness
    0.31
     closely
    0.29
    /context
    0.27
    plevel
    0.25
    å¯ĨåĪĩ
    0.25
    åIJĥä»Ģä¹Ī
    0.25
    对ä»ĸ们
    0.25
    ew
    0.24
    hi
    0.24
    Activations Density 1.816%

    No Known Activations