© 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. 4-TRANSCODER-HP
    7. 209
    Prev
    Next
    INDEX
    Explanations

    ishes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sey
    -0.26
    èĩ£
    -0.25
    ä¸ĭåįĬ
    -0.25
    onde
    -0.24
    <html
    -0.24
    >Last
    -0.24
    pike
    -0.23
    èµĽ
    -0.23
    å¼ķ
    -0.23
    ä½Ļ
    -0.23
    POSITIVE LOGITS
    loon
    0.31
    /art
    0.26
    éľĢè¦ģçĶ¨åĪ°
    0.26
     Loft
    0.26
    VersionUID
    0.25
    éĵ©
    0.24
    龸çİĭ
    0.24
    椤
    0.23
     Smithsonian
    0.23
     Sistema
    0.23
    Activations Density 0.083%

    No Known Activations