© 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. 161817
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    terr
    -0.26
    åı¦å¤ĸä¸Ģ个
    -0.25
    asant
    -0.25
     возд
    -0.23
    åĿĩçĶ±
    -0.23
    åįģåĪĨéĴŁ
    -0.23
    第äºĮç§į
    -0.23
    Compat
    -0.23
     Muss
    -0.23
    ihn
    -0.23
    POSITIVE LOGITS
    IJľ
    0.26
    <ll
    0.23
     Oliv
    0.23
    ities
    0.23
    çĪ±åĽ½
    0.23
    è¿ĩåħ³
    0.23
     BMC
    0.23
     organisers
    0.22
    Ŀå§ĭ
    0.22
    lang
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.