© 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. 19-TRANSCODER-HP
    7. 5800
    Prev
    Next
    INDEX
    Explanations

    Arab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auty
    -0.33
    æĹĹèĪ°
    -0.26
     Charleston
    -0.26
    çĶ©
    -0.25
    åľ³
    -0.25
    åī©
    -0.24
    aunch
    -0.24
    便ä¼ļ
    -0.24
    便æĺ¯
    -0.24
    eter
    -0.24
    POSITIVE LOGITS
    amon
    0.26
     dÄ±ÅŁÄ±
    0.26
    -Cs
    0.25
    LLU
    0.24
    åħ¸
    0.24
    å¤§åĽ½
    0.24
    uchos
    0.24
    earch
    0.24
    çĿ¹
    0.23
    祸
    0.23
    Activations Density 2.345%

    No Known Activations