© 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. 163154
    Prev
    Next
    INDEX
    Explanations

    England place names

    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
    auce
    -0.27
    grounds
    -0.27
    olta
    -0.26
    åī¯ä¸»ä»»
    -0.26
    oplayer
    -0.25
    ilogue
    -0.25
    ãĤ¿ãĤ¤
    -0.25
    Äĩi
    -0.25
    ãĤ·ãĥ¼
    -0.24
    hetic
    -0.24
    POSITIVE LOGITS
     dominated
    0.28
     Scientific
    0.27
     independently
    0.27
     Coding
    0.26
    æ²³
    0.25
     Bang
    0.25
    -flag
    0.24
    orman
    0.24
     attracting
    0.24
    -region
    0.24
    Activations Density 0.059%

    No Known Activations