© 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. 35-TRANSCODER-HP
    7. 40669
    Prev
    Next
    INDEX
    Explanations

    say "st" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     *__
    -0.27
     requis
    -0.26
     outr
    -0.26
     masturbation
    -0.24
    -bin
    -0.24
     utilized
    -0.24
    mast
    -0.24
     outgoing
    -0.23
     nutshell
    -0.23
     lab
    -0.22
    POSITIVE LOGITS
     st
    0.52
     cleaner
    0.34
    ep
    0.32
    ope
    0.30
     Cleaner
    0.30
     te
    0.29
    eper
    0.29
    uer
    0.29
    clo
    0.29
    ptions
    0.29
    Activations Density 0.036%

    No Known Activations