© 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. 27-TRANSCODER-HP
    7. 57099
    Prev
    Next
    INDEX
    Explanations

    customers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺ¶
    -0.28
    uish
    -0.27
    祺
    -0.26
    inan
    -0.25
    ermal
    -0.24
    mil
    -0.24
    -body
    -0.24
    idis
    -0.24
     sol
    -0.24
     restructuring
    -0.24
    POSITIVE LOGITS
     customers
    0.36
    å¸ĤåľºéľĢæ±Ĥ
    0.35
    客æĪ·éľĢæ±Ĥ
    0.32
     consumers
    0.30
    éľĢæ±Ĥ
    0.29
     tastes
    0.29
    æĵį
    0.29
     Customers
    0.29
     buyers
    0.29
     customer
    0.29
    Activations Density 0.005%

    No Known Activations