© 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. 25-TRANSCODER-HP
    7. 107309
    Prev
    Next
    INDEX
    Explanations

    attributed quotes or sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ofile
    -0.26
    osa
    -0.26
    instanc
    -0.25
     bushes
    -0.25
    anter
    -0.25
     overwrite
    -0.24
     Unidos
    -0.24
    å¡Į
    -0.24
    .Msg
    -0.24
    orque
    -0.24
    POSITIVE LOGITS
     student
    0.27
    assin
    0.27
    ãģĦãģ¾
    0.26
     Haz
    0.26
     hurt
    0.24
     cur
    0.24
     pupil
    0.24
     rag
    0.24
    -c
    0.24
     pol
    0.24
    Activations Density 0.898%

    No Known Activations