© 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. 5042
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    disposing
    -0.28
     extrad
    -0.28
    bits
    -0.25
    _EXTERN
    -0.24
    è±Ĩçĵ£
    -0.24
     Pru
    -0.24
    ittal
    -0.24
    .indexOf
    -0.23
     Humb
    -0.23
    ordan
    -0.23
    POSITIVE LOGITS
    %f
    0.27
    å¦Ļ
    0.26
    åĵ©
    0.25
    éħįå¥Ĺ设æĸ½
    0.24
     SDL
    0.24
    åĿIJ
    0.24
    alleries
    0.24
    ило
    0.24
    =l
    0.24
    nf
    0.23
    Activations Density 0.016%

    No Known Activations