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. 654
    Prev
    Next
    INDEX
    Explanations

    Scientific texts

    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
     m
    -0.31
     https
    -0.31
     
    -0.31
     st
    -0.30
     b
    -0.27
     a
    -0.27
     g
    -0.27
     res
    -0.27
     I
    -0.27
     d
    -0.27
    POSITIVE LOGITS
    onsense
    0.28
    åĪ·
    0.26
    formation
    0.26
    æīĵ好
    0.26
    terms
    0.25
    ptime
    0.25
    irc
    0.24
    ague
    0.24
    habit
    0.24
    .energy
    0.24
    Activations Density 0.136%

    No Known Activations