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. 14934
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    宣
    -0.27
     poll
    -0.26
    éĢł
    -0.26
    .Mapping
    -0.25
     bottoms
    -0.25
    -conf
    -0.25
     deliberate
    -0.24
    	callback
    -0.24
    .callback
    -0.24
    绿
    -0.24
    POSITIVE LOGITS
    azen
    0.30
    mat
    0.27
     á»ķ
    0.26
     Bitte
    0.26
     Äijám
    0.25
    itus
    0.24
    çĬ¶åĨµ
    0.24
    èµĸ
    0.24
    jal
    0.24
     Come
    0.23
    Activations Density 0.087%

    No Known Activations

    This feature has no known activations.