© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89622
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¸®ä½ł
    -0.33
    éĻªä½ł
    -0.32
     reliable
    -0.30
    ç»Ļä½ł
    -0.30
     Foundations
    -0.29
    inan
    -0.28
    å¯¹ä½ł
    -0.28
    è®©ä½ł
    -0.27
    requests
    -0.27
    è·Łä½ł
    -0.27
    POSITIVE LOGITS
    izione
    0.29
     zb
    0.28
    离å¼ĢäºĨ
    0.26
     chaining
    0.25
     chain
    0.25
    nels
    0.25
    .catch
    0.24
    åľ¨éĩĮéĿ¢
    0.24
     clipboard
    0.24
    овиÑĩ
    0.24
    Activations Density 40.091%

    No Known Activations