© 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. 174
    Prev
    Next
    INDEX
    Explanations

    of

    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
    åŀĤ
    -0.25
     Carroll
    -0.25
    rif
    -0.24
    åĪ°æľĢåIJİ
    -0.24
    -definition
    -0.24
    æ¤Ń
    -0.23
    åĪ¹éĤ£
    -0.23
    PELL
    -0.23
    enus
    -0.23
     '*',
    -0.23
    POSITIVE LOGITS
    inger
    0.27
    arma
    0.26
    èĥģ
    0.25
    lio
    0.24
    æĿĤ
    0.24
    ÑģÑĤвие
    0.24
    cent
    0.24
    (AP
    0.24
    认è¯ĨåĪ°
    0.24
    é®®
    0.23
    Activations Density 0.066%

    No Known Activations