© 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. 157
    Prev
    Next
    INDEX
    Explanations

    Parm/Parry/Parma

    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
    ä¸į便
    -0.31
    .vars
    -0.26
    VEL
    -0.25
    sj
    -0.25
    å·®è·Ŀ
    -0.24
     Jacqu
    -0.24
     volont
    -0.24
    ä¸ĩåIJį
    -0.23
    oref
    -0.23
    å¯ĮåĬĽ
    -0.23
    POSITIVE LOGITS
    æ¯ı
    0.27
    fest
    0.25
    mentioned
    0.24
    oka
    0.24
    ña
    0.24
    æį£
    0.23
    寥
    0.23
     Prepared
    0.23
    æļ´
    0.23
    身å¿ĥåģ¥åº·
    0.23
    Activations Density 0.114%

    No Known Activations