© 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. 5205
    Prev
    Next
    INDEX
    Explanations

    testing, trying things out

    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
    طة
    -0.27
    æĶ¾æīĭ
    -0.27
    å±ĢéĻIJ
    -0.25
    uv
    -0.24
     Boh
    -0.24
    çĶ¨çĶµ
    -0.24
    uvw
    -0.24
     teng
    -0.24
    è°Ĺ
    -0.24
    ubo
    -0.23
    POSITIVE LOGITS
     Printable
    0.26
    angible
    0.26
    çį
    0.26
    åĮ¯
    0.25
    egend
    0.25
    Report
    0.24
     Printed
    0.24
     alternate
    0.24
    FindObject
    0.24
    趾
    0.24
    Activations Density 0.011%

    No Known Activations