© 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. 5332
    Prev
    Next
    INDEX
    Explanations

    Something is necessary

    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
    CHASE
    -0.25
    æľĪ以æĿ¥
    -0.25
    çĶŁæĪIJ
    -0.25
    OSE
    -0.25
    lider
    -0.24
    OPTIONS
    -0.23
    è¯Ń
    -0.23
    åİŁå§ĭ
    -0.23
     mirrored
    -0.23
    ames
    -0.23
    POSITIVE LOGITS
     desn
    0.28
    çĢĽ
    0.28
    顺åĪ©å®ĮæĪIJ
    0.27
    olland
    0.25
    atin
    0.25
     needless
    0.25
    åĬŁè¯¾
    0.24
    æ´²
    0.24
    滿
    0.24
     someday
    0.24
    Activations Density 0.012%

    No Known Activations