© 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. 23-TRANSCODER-HP
    7. 161888
    Prev
    Next
    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帧
    -0.23
    å½
    -0.22
    ELY
    -0.22
    å¦Ĥæŀľçݩ家
    -0.22
    Exclusive
    -0.21
    å¾Īå¤ļæľĭåıĭ
    -0.21
    [frame
    -0.21
    Mutable
    -0.20
    éra
    -0.20
    åİŁæĸĩ
    -0.20
    POSITIVE LOGITS
    <|endoftext|>
    0.27
    ï¼Ī
    0.27
    -
    0.23
     (
    0.23
    **↵
    0.23
    :
    0.23
    âĢ¦
    0.23
    -side
    0.23
    /
    0.22
    ()č↵
    0.22
    Activations Density 0.001%

    No Known Activations