© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163473
    Prev
    Next
    INDEX
    Explanations

    Prefix "eu"

    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
    åŁ¹åħ»åѦçĶŁ
    -0.29
    éĢ¼
    -0.28
     Bain
    -0.28
    æĥħ
    -0.24
    æŀ¯
    -0.24
    ä¸Ģå±Ĥ
    -0.24
    è§Ħ
    -0.24
     mü
    -0.23
    éĩı
    -0.23
    äºĴ
    -0.23
    POSITIVE LOGITS
    y
    0.32
    enal
    0.27
    pcf
    0.26
    .getResource
    0.25
    yre
    0.25
    eness
    0.24
     getResource
    0.24
    лик
    0.24
     mingle
    0.24
    ponsor
    0.24
    Activations Density 0.024%

    No Known Activations