© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23431
    Prev
    Next
    INDEX
    Explanations

    diverse problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥľä»»
    -0.29
    æľĢå¿«çļĦ
    -0.27
    çŃīå¾ħ
    -0.25
     SEQ
    -0.24
     welcome
    -0.24
     Nass
    -0.24
     паÑĢа
    -0.23
    onitor
    -0.23
    pres
    -0.23
    æĤ¼
    -0.23
    POSITIVE LOGITS
    ouri
    0.29
    enen
    0.25
    饱满
    0.25
     ener
    0.25
     continent
    0.25
    ä¿Ŀè¯ģéĩij
    0.24
     provincia
    0.24
    ration
    0.24
    ä½łçľĭ
    0.24
     Continental
    0.24
    Activations Density 0.002%

    No Known Activations