© 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. 22-TRANSCODER-HP
    7. 112309
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ°ĶåĢĻ
    -0.33
    æľī害
    -0.30
    çĽ²çĽ®
    -0.29
     clim
    -0.29
     dys
    -0.28
    çĨ¬å¤ľ
    -0.28
    害
    -0.28
     due
    -0.28
    åĬ£
    -0.27
    æļ´éľ²
    -0.27
    POSITIVE LOGITS
    endir
    0.28
    emens
    0.27
     matt
    0.26
    tent
    0.26
    Tk
    0.26
    ocial
    0.25
    social
    0.25
    æ¸İ
    0.25
    à¹ĩà¸Ķ
    0.24
    epam
    0.24
    Activations Density 0.001%

    No Known Activations