© 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. 23-TRANSCODER-HP
    7. 161972
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èıŁ
    -0.26
    ä¸Ģçľĭ
    -0.26
    åĮ»ç§ij
    -0.26
     Saves
    -0.25
    è¦ģçľĭ
    -0.25
     whom
    -0.25
    åĵªåĦ¿
    -0.24
     Casc
    -0.24
    éĴĪ对æĢ§
    -0.24
    olem
    -0.24
    POSITIVE LOGITS
    oenix
    0.29
     renamed
    0.28
     implemented
    0.28
    ilities
    0.27
     invested
    0.27
    å¼Ł
    0.26
     Ministers
    0.26
    estre
    0.25
     purified
    0.24
    ìĹŃ
    0.24
    Activations Density 0.001%

    No Known Activations