© 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. 35
    Prev
    Next
    INDEX
    Explanations

    Dudley

    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
    åĢŁ
    -0.25
    åij¼åĴĮ
    -0.25
    why
    -0.24
    roup
    -0.24
    çıŃ级
    -0.24
    LLU
    -0.24
    åŀĭ
    -0.23
     Whisper
    -0.23
    istory
    -0.23
     franchises
    -0.23
    POSITIVE LOGITS
     distr
    0.30
     Earl
    0.28
    åĪĨå¸ĥ
    0.25
    Destroyed
    0.24
     Arts
    0.24
     universal
    0.23
    ENE
    0.23
    jack
    0.23
    earth
    0.23
    antino
    0.23
    Activations Density 0.022%

    No Known Activations