© 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. 5838
    Prev
    Next
    INDEX
    Explanations

    Unique

    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
    ç¢İçīĩ
    -0.27
    spo
    -0.27
    oss
    -0.24
    rai
    -0.23
    mania
    -0.23
     skl
    -0.23
     negativity
    -0.23
    çĻ½éĵ¶
    -0.23
    æļĹ
    -0.23
    Null
    -0.23
    POSITIVE LOGITS
    ided
    0.26
     wise
    0.26
    ersistence
    0.26
     worrying
    0.26
     Cord
    0.26
    [assembly
    0.26
     zab
    0.25
     convincing
    0.25
    rawing
    0.25
    enet
    0.24
    Activations Density 0.008%

    No Known Activations