© 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. 163070
    Prev
    Next
    INDEX
    Explanations

    discrim

    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
    WER
    -0.26
    æ°¸ä¹ħ
    -0.26
    wer
    -0.26
    寸
    -0.25
    éĶ®çĽĺ
    -0.25
    erty
    -0.25
    ä¸Ģç»ı
    -0.25
    ester
    -0.24
    éķ¿çĽ¸
    -0.24
    fern
    -0.24
    POSITIVE LOGITS
    æĭīæĸ¯
    0.30
    æ§
    0.28
    NoSuch
    0.25
     cad
    0.25
     matchmaking
    0.25
    isphere
    0.25
    ly
    0.25
    çļĦ缮åħī
    0.24
    æĢ§å¼º
    0.24
     trải
    0.24
    Activations Density 0.074%

    No Known Activations