© 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. 5873
    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
     recall
    -0.29
    缸åħ³æĸ°éĹ»
    -0.27
     back
    -0.26
     CDs
    -0.26
     gated
    -0.25
    pling
    -0.25
     dep
    -0.25
     naturally
    -0.25
    æĸ¯åŁº
    -0.25
    =false
    -0.24
    POSITIVE LOGITS
    ecc
    0.27
    enne
    0.26
    imes
    0.26
    èŀĤ
    0.26
    glich
    0.26
    LL
    0.25
     htmlentities
    0.25
    顽
    0.25
    ulos
    0.24
    æį·
    0.23
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.