© 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. 161679
    Prev
    Next
    INDEX
    Explanations

    Pain

    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
    èIJ½
    -0.28
    Junior
    -0.26
    eut
    -0.26
     junior
    -0.25
    åĿį
    -0.25
     cinemat
    -0.25
    -away
    -0.25
     Fountain
    -0.25
     vo
    -0.24
    æ§ĭ
    -0.24
    POSITIVE LOGITS
    Terms
    0.32
    ersive
    0.29
    _sb
    0.28
     painful
    0.27
    acs
    0.27
    çĹĽèĭ¦
    0.27
    累累
    0.27
    éĩįè¦ģ举æݪ
    0.26
    pain
    0.26
    .orig
    0.26
    Activations Density 0.011%

    No Known Activations