© 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. 161694
    Prev
    Next
    INDEX
    Explanations

    People are mentioned

    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
    å¤Ħäºİ
    -0.32
     gerekt
    -0.30
     conte
    -0.27
    cio
    -0.27
     Anglo
    -0.26
    éĿ¢åīį
    -0.26
     Ree
    -0.25
    éľĢè¦ģ
    -0.25
    usch
    -0.25
    atomy
    -0.25
    POSITIVE LOGITS
    æ§Ľ
    0.27
     nightly
    0.25
    è¾Ľ
    0.25
    è¾Ľè¾£
    0.25
    bst
    0.25
    åħ¬æĬ¥
    0.25
    MethodInfo
    0.25
    stag
    0.24
    çłĶ究æĬ¥åijĬ
    0.24
    alendar
    0.24
    Activations Density 0.002%

    No Known Activations