© 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. 163402
    Prev
    Next
    INDEX
    Explanations

    pal

    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
    lations
    -0.28
     BaseService
    -0.26
     signatures
    -0.26
     signer
    -0.25
     Äijá»Ŀi
    -0.25
    æīĵåİĭ
    -0.24
     signature
    -0.24
     demol
    -0.24
    IDES
    -0.24
    çĮ«
    -0.23
    POSITIVE LOGITS
    ymax
    0.28
     aisle
    0.27
    室å¤ĸ
    0.27
    _corner
    0.26
     shade
    0.25
     corridor
    0.25
    -sheet
    0.25
    UCT
    0.24
    endency
    0.24
    室
    0.24
    Activations Density 0.100%

    No Known Activations