© 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. 161915
    Prev
    Next
    INDEX
    Explanations

    Ellipses and bad formatting

    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
    olis
    -0.27
    ï¼ļ<
    -0.26
    uchen
    -0.26
    oli
    -0.26
    pta
    -0.26
    poi
    -0.25
    åįĵ
    -0.25
    /owl
    -0.25
     WC
    -0.24
    .*)
    -0.24
    POSITIVE LOGITS
     potentially
    0.25
    æĸ©
    0.25
    ï¸
    0.25
    –
    0.24
    åĪĨè¡Į
    0.23
    веÑĢ
    0.23
     Terraria
    0.22
    estate
    0.22
     Heights
    0.22
    _None
    0.22
    Activations Density 0.048%

    No Known Activations