© 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. 5464
    Prev
    Next
    INDEX
    Explanations

    1

    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
    驳
    -0.29
     xa
    -0.26
     respect
    -0.26
    æľŁè´§
    -0.25
    swire
    -0.24
    Nd
    -0.24
    -olds
    -0.24
    å®ĮæĪIJäºĨ
    -0.23
    porte
    -0.23
    mods
    -0.23
    POSITIVE LOGITS
    YST
    0.27
    gard
    0.26
    .footer
    0.26
    çĥŁåĽ±
    0.24
     Victoria
    0.24
    gst
    0.24
    çĶĺ
    0.24
     referring
    0.24
     Bloody
    0.24
    ARING
    0.23
    Activations Density 0.059%

    No Known Activations