© 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. 20-TRANSCODER-HP
    7. 64133
    Prev
    Next
    INDEX
    Explanations

    conversational and formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pike
    -0.26
    æĸ°å½¢åĬ¿
    -0.25
    ä¸įéĢĤ
    -0.24
    кÑĢаÑģ
    -0.24
    æ¯ıå¹´éĥ½
    -0.24
    æĬĬæīĭ
    -0.24
     Year
    -0.24
     Fres
    -0.24
    ä»ħä¾Ľ
    -0.23
    åĨįè§ģ
    -0.23
    POSITIVE LOGITS
    pod
    0.28
     ess
    0.28
    adora
    0.26
    avid
    0.25
    oodle
    0.25
    ICES
    0.24
    egasus
    0.24
    çķĶ
    0.24
    ria
    0.24
    pow
    0.24
    Activations Density 1.744%

    No Known Activations