© 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. 5700
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ham
    -0.28
    HAM
    -0.27
    çĻ¾å¹´
    -0.27
    ä¸Ģä¸Ŀ
    -0.26
    %!
    -0.25
    lingen
    -0.25
    大å¹ħ度
    -0.24
    å®ĺåijĺ
    -0.24
    |R
    -0.24
    ç¿»
    -0.24
    POSITIVE LOGITS
    astes
    0.28
    ading
    0.27
    忱
    0.27
    ophage
    0.26
    beiter
    0.26
    ç³ł
    0.24
    ieber
    0.24
    主治
    0.24
    以èĩ´
    0.24
    çĺħ
    0.24
    Activations Density 0.102%

    No Known Activations

    This feature has no known activations.