© 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. 23-TRANSCODER-HP
    7. 24676
    Prev
    Next
    INDEX
    Explanations

    words ending in "ing"

    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
     tends
    -0.32
     done
    -0.28
     meticulously
    -0.28
    é¹ħ
    -0.26
     definitely
    -0.26
    either
    -0.26
    ded
    -0.26
    á»ĩ
    -0.25
    atchet
    -0.25
    æĺ¯æ¯Ķè¾ĥ
    -0.25
    POSITIVE LOGITS
     Tu
    0.33
    cott
    0.31
     Diss
    0.30
     Og
    0.29
     Your
    0.26
     Solar
    0.25
     Der
    0.25
     Cass
    0.25
     Pl
    0.25
    åĬ¢
    0.25
    Activations Density 0.016%

    No Known Activations