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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161835
    Prev
    Next
    INDEX
    Explanations

    Cancellation

    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
    trust
    -0.28
    gest
    -0.25
     trusts
    -0.25
    çŁ³æ¦´
    -0.24
     trần
    -0.24
    ldr
    -0.24
    åºŀ
    -0.24
    ivery
    -0.24
    å±Ģ
    -0.24
    èĥ´
    -0.24
    POSITIVE LOGITS
     cancel
    0.81
     cancellation
    0.78
     cancell
    0.71
     Cancel
    0.70
     canc
    0.69
     canceled
    0.68
     cancelling
    0.68
     cancelled
    0.66
    cancel
    0.65
    Cancel
    0.62
    Activations Density 0.002%

    No Known Activations