© 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. 162652
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    esters
    -0.28
     tắt
    -0.25
    éĩįè¦ģåİŁåĽł
    -0.25
     resources
    -0.25
    èµĦæĸĻæĺ¾ç¤º
    -0.25
    kal
    -0.25
    åѦçĶŁä»¬
    -0.24
    iasm
    -0.24
    érique
    -0.24
     people
    -0.24
    POSITIVE LOGITS
    год
    0.28
    .WriteByte
    0.27
    ug
    0.26
    åħ«åŃĹ
    0.25
    ut
    0.25
     circuit
    0.25
     cas
    0.24
    æµģçķħ
    0.23
    _IS
    0.23
    对è¯Ŀ
    0.23
    Activations Density 0.000%

    No Known Activations