© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54515
    Prev
    Next
    INDEX
    Explanations

    say the ending -ing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charging
    -0.51
     typing
    -0.50
     coding
    -0.49
    	logging
    -0.49
     riding
    -0.49
    ailing
    -0.49
     wrapping
    -0.49
     flying
    -0.49
     jumping
    -0.48
     playing
    -0.48
    POSITIVE LOGITS
    leared
    0.30
    ROLS
    0.28
    rames
    0.28
    _CAPTURE
    0.28
    urette
    0.27
    ypse
    0.27
    lies
    0.26
    ниÑĨÑĭ
    0.26
    èij©
    0.26
    odiac
    0.26
    Activations Density 0.009%

    No Known Activations