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. 3027
    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
    æĥħåĨµè¿Ľè¡Į
    -0.28
    cloud
    -0.25
    è¿Ľè¡Įåħ¨éĿ¢
    -0.24
    itledBorder
    -0.24
    иÑİ
    -0.24
     Dahl
    -0.24
     Circ
    -0.24
    noc
    -0.24
    bell
    -0.23
    izen
    -0.23
    POSITIVE LOGITS
    trx
    0.30
     câ
    0.24
    åĿij
    0.24
     ARGS
    0.24
    -css
    0.24
    æŀŀ
    0.24
     ou
    0.23
     unf
    0.23
     cancers
    0.23
     will
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.