© 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. 162884
    Prev
    Next
    INDEX
    Explanations

    Tutorials or software use

    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
    /apis
    -0.27
    eton
    -0.27
    DOMContentLoaded
    -0.25
    岸
    -0.24
     freedoms
    -0.24
    çł
    -0.24
    веÑģÑĤ
    -0.24
    VED
    -0.24
     exposures
    -0.24
    ÐłÐķ
    -0.24
    POSITIVE LOGITS
     Simple
    0.33
     joins
    0.28
     Currency
    0.27
    currency
    0.27
     Salary
    0.27
     annex
    0.27
    inst
    0.27
    åĴİ
    0.26
     {.
    0.26
     inst
    0.26
    Activations Density 0.012%

    No Known Activations