© 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. 5940
    Prev
    Next
    INDEX
    Explanations

    Code, snippets, dates, numbers

    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
    åı¯æݧ
    -0.26
    .isArray
    -0.26
    ewidth
    -0.26
    rove
    -0.26
    Abort
    -0.25
    çī¹çĤ¹
    -0.25
    æ¢ħèĬ±
    -0.25
    him
    -0.24
    Om
    -0.24
    -parts
    -0.24
    POSITIVE LOGITS
     instantly
    0.27
     DependencyProperty
    0.26
     indifferent
    0.24
    çĭ¬
    0.24
     Friday
    0.24
     Saturday
    0.24
    RAY
    0.23
    urn
    0.23
     richest
    0.23
    è¿Ļä¸Ģ天
    0.23
    Activations Density 0.002%

    No Known Activations