© 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. 23-TRANSCODER-HP
    7. 162357
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ợi
    -0.29
    otch
    -0.28
    ensch
    -0.27
    dzi
    -0.27
    emens
    -0.26
    assi
    -0.26
    orra
    -0.26
    ÅĤo
    -0.25
    çĶŁäº§çĶŁæ´»
    -0.25
    onders
    -0.25
    POSITIVE LOGITS
    éĢIJ
    0.27
    ê°ģ
    0.27
    åĢ¾
    0.27
    Behind
    0.27
    纸
    0.25
    -Smith
    0.25
    å¹ķåIJİ
    0.25
     ê°ľ
    0.25
     iter
    0.24
    paper
    0.24
    Activations Density 0.002%

    No Known Activations