© 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. 298
    Prev
    Next
    INDEX
    Explanations

    inal

    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
    éªŀ
    -0.26
    æķĪåºĶ
    -0.26
    æľī人
    -0.26
    éļ§éģĵ
    -0.26
    ean
    -0.25
    /mat
    -0.25
    Mat
    -0.25
     shape
    -0.25
    antee
    -0.25
    âĪĪ
    -0.25
    POSITIVE LOGITS
     discriminator
    0.30
    ä¸Ģ级
    0.27
    nett
    0.27
    avra
    0.26
    *this
    0.25
    被æ·ĺæ±°
    0.24
     offered
    0.24
    samples
    0.24
    etur
    0.24
     Among
    0.24
    Activations Density 0.009%

    No Known Activations