© 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. 5906
    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
    ivers
    -0.29
    ycastle
    -0.28
    ve
    -0.27
     "}
    -0.26
    ansa
    -0.26
    zers
    -0.26
    ä¸įå®ļ
    -0.25
    åĬĽ
    -0.25
     wheels
    -0.24
    EVER
    -0.24
    POSITIVE LOGITS
    åĪĨ离
    0.26
    容纳
    0.25
    çĥŃçĪ±
    0.25
    åħ¬è®¤
    0.25
    æłı缮
    0.24
    TRS
    0.23
    rire
    0.23
    é²ľæ´»
    0.23
    离
    0.23
    æݥ纳
    0.23
    Activations Density 0.040%

    No Known Activations

    This feature has no known activations.