© 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. 162572
    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
    åıĪ被
    -0.27
     Kv
    -0.27
     Carp
    -0.25
     empir
    -0.25
    enco
    -0.24
    人寿
    -0.24
     KW
    -0.24
    infer
    -0.24
    /***
    -0.24
    SWG
    -0.24
    POSITIVE LOGITS
    rzy
    0.27
    ality
    0.27
    çļĦæĥħæĦŁ
    0.27
    å¸Ĥåľºä¸»ä½ĵ
    0.27
     Affero
    0.26
     conflict
    0.26
    bane
    0.25
    æĬ¼
    0.25
    ity
    0.24
     stake
    0.24
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.