© 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. 162843
    Prev
    Next
    INDEX
    Explanations

    physical descriptions

    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
    wu
    -0.26
    ниÑĨ
    -0.25
    æŃ¥
    -0.24
    ingly
    -0.24
     hứng
    -0.24
    atica
    -0.24
    uids
    -0.24
    ниÑĩ
    -0.24
     themselves
    -0.23
    究
    -0.23
    POSITIVE LOGITS
    éĤ£äºĽ
    0.28
    è¿ĻæĶ¯
    0.28
     centrally
    0.25
    kul
    0.25
     fle
    0.24
    ses
    0.24
    cha
    0.24
     implemented
    0.24
    vsp
    0.24
    _ly
    0.24
    Activations Density 0.036%

    No Known Activations