© 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. 161774
    Prev
    Next
    INDEX
    Explanations

    do

    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
    rama
    -0.28
    hee
    -0.27
    è´½
    -0.25
    ä¸ĵåľº
    -0.25
    fang
    -0.25
    azz
    -0.24
    errated
    -0.24
    FormControl
    -0.24
    ermann
    -0.23
    ingleton
    -0.23
    POSITIVE LOGITS
    åªĴ
    0.28
    æĥħ
    0.27
     arts
    0.26
     advise
    0.26
     Implicit
    0.25
     sı
    0.25
     explicit
    0.25
     advice
    0.25
    åĥıæĺ¯
    0.24
    duce
    0.24
    Activations Density 0.002%

    No Known Activations