© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89724
    Prev
    Next
    INDEX
    Explanations

    Punctuation and "no"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignored
    -0.28
    gang
    -0.26
    yclopedia
    -0.26
    ignet
    -0.26
    chy
    -0.26
    antar
    -0.25
    nage
    -0.25
    irse
    -0.25
     Vi
    -0.24
     ourselves
    -0.24
    POSITIVE LOGITS
    çIJ´
    0.29
    åħĪè¡Į
    0.26
    éģį
    0.25
    æ³ķåºŃ
    0.25
     cert
    0.24
    ä»İä¸ļ
    0.24
     arb
    0.24
    ä¿Ŀå¯Ĩ
    0.23
     Revolution
    0.23
     jspb
    0.23
    Activations Density 16.965%

    No Known Activations