© 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. 52612
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    Negative Logits
    mer
    -0.30
    ìĬ¬
    -0.29
    metic
    -0.28
    levator
    -0.28
    jal
    -0.28
    ramids
    -0.27
    sass
    -0.27
     sticking
    -0.27
     conscient
    -0.26
    _met
    -0.25
    POSITIVE LOGITS
     des
    0.29
     integral
    0.27
     der
    0.27
     components
    0.26
    åĽłåľ°
    0.26
     dil
    0.25
     dile
    0.25
     deb
    0.24
    components
    0.23
    æģ¢
    0.23
    Activations Density 0.032%

    No Known Activations