© 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. 4-TRANSCODER-HP
    7. 58
    Prev
    Next
    INDEX
    Explanations

    negative experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lien
    -0.29
    arsed
    -0.26
    ughter
    -0.25
     disproportion
    -0.25
     alerted
    -0.24
    åį¡çīĩ
    -0.24
    elmet
    -0.24
     давно
    -0.24
    ffects
    -0.23
    éļľ
    -0.23
    POSITIVE LOGITS
     pros
    0.26
     forg
    0.26
    稳åģ¥
    0.25
     revis
    0.25
     exclusive
    0.25
    .ke
    0.24
    æ²ĥ
    0.24
    æľ¬åĽ½
    0.24
     Tent
    0.24
    val
    0.23
    Activations Density 0.169%

    No Known Activations