Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 7469
    Prev
    Next
    INDEX
    Explanations

    monitoring

    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
    иÑģк
    -0.28
    ä¸Ģ页
    -0.28
     CONTRIBUTORS
    -0.28
     Answers
    -0.27
    printed
    -0.27
     Writers
    -0.26
     ÑģкаÑĩ
    -0.26
    lico
    -0.25
    强çĥĪ
    -0.24
    istles
    -0.24
    POSITIVE LOGITS
    çĽijæµĭ
    0.34
     monitoring
    0.32
    s
    0.30
     monitor
    0.30
    çĽijæİ§
    0.28
    monitor
    0.28
    ousse
    0.26
     scheme
    0.25
    gue
    0.25
    Vue
    0.25
    Activations Density 0.124%

    No Known Activations