© 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. 5318
    Prev
    Next
    INDEX
    Explanations

    Code and references

    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
    ince
    -0.26
     вÑģÑıк
    -0.25
    brace
    -0.25
    Bring
    -0.25
    ä¼ļå±ķ
    -0.25
    acz
    -0.24
    çĿ£å¯¼
    -0.24
    illy
    -0.24
     Bring
    -0.24
    ä»
    -0.24
    POSITIVE LOGITS
    çijķçĸµ
    0.27
    Âł
    0.27
     Âł
    0.26
    åİ¿åħ¬å®īå±Ģ
    0.26
     obten
    0.25
    vore
    0.25
    hread
    0.25
    лÑıеÑĤ
    0.24
    mat
    0.24
     bul
    0.24
    Activations Density 0.047%

    No Known Activations