© 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. 6157
    Prev
    Next
    INDEX
    Explanations

    Numbers and codes

    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
    DEFINE
    -0.25
     sourceMappingURL
    -0.25
     Rath
    -0.25
    lasses
    -0.24
    пÑĥÑĤ
    -0.24
    åħ¥åºĵ
    -0.24
    å©´
    -0.23
    Ùģت
    -0.23
     Appeals
    -0.23
    溧
    -0.22
    POSITIVE LOGITS
    ulum
    0.30
    "+"
    0.26
    æĺİæľĹ
    0.26
    nea
    0.26
    ä¹ĭä½Ļ
    0.25
    plusplus
    0.24
     Vera
    0.24
    çŃīåĬŁèĥ½
    0.24
    erness
    0.24
    DataRow
    0.23
    Activations Density 0.002%

    No Known Activations