© 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. 6029
    Prev
    Next
    INDEX
    Explanations

    computer options/instructions

    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
    nock
    -0.26
    åŃĹ第
    -0.25
     instantly
    -0.25
     autos
    -0.24
    ä¸ŃåįĪ
    -0.24
    éĢģè¾¾
    -0.24
     Suff
    -0.23
    åıĹä¸įäºĨ
    -0.23
    oday
    -0.23
    CardContent
    -0.23
    POSITIVE LOGITS
    SSI
    0.26
     elkaar
    0.25
     pur
    0.25
    mia
    0.25
    alties
    0.25
     chute
    0.25
    è´´
    0.24
    tem
    0.24
    liche
    0.24
    TEM
    0.24
    Activations Density 0.025%

    No Known Activations