© 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. 162614
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    Ø°
    -0.28
    ört
    -0.26
    ä¹Łæĺ¯
    -0.24
    rap
    -0.24
    -che
    -0.23
    CHAT
    -0.23
    éĢļæĬ¥
    -0.23
    è¡Įäºĭ
    -0.23
    ITE
    -0.23
    brig
    -0.23
    POSITIVE LOGITS
    /respond
    0.30
    ntax
    0.27
     what
    0.26
    ä»Ģä¹Īåı«
    0.26
    aptic
    0.26
    ä¸Ģ代
    0.26
    eno
    0.26
     balancing
    0.25
    åŁİ乡
    0.25
    cem
    0.25
    Activations Density 0.002%

    No Known Activations