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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7332
    Prev
    Next
    INDEX
    Explanations

    Requirements/recommendations

    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
    è¢Ĥ
    -0.29
    INGER
    -0.26
     Nug
    -0.25
    antry
    -0.25
    emaakt
    -0.24
    removeClass
    -0.24
    åĬ¨çĶŁæĪIJ
    -0.24
    åįĥä¼ı
    -0.23
    EGA
    -0.23
    箧
    -0.23
    POSITIVE LOGITS
    è¦ģæ±Ĥ
    0.44
     requirements
    0.43
     requirement
    0.42
     Requirements
    0.40
    å¿ħé¡»
    0.39
     required
    0.39
     must
    0.39
     Requirement
    0.38
     require
    0.36
    å¿ħéľĢ
    0.36
    Activations Density 0.196%

    No Known Activations