© 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. 25-TRANSCODER-HP
    7. 108387
    Prev
    Next
    INDEX
    Explanations

    Code and academic papers

    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
     trial
    -0.27
    åıijå±ķ缮æłĩ
    -0.27
    irie
    -0.27
    stroke
    -0.25
    developer
    -0.25
    å±ŀ
    -0.24
    inals
    -0.24
     developer
    -0.24
    æľºåĬ¨
    -0.24
    enza
    -0.24
    POSITIVE LOGITS
    sse
    0.26
     politic
    0.25
    Diff
    0.25
    尤为
    0.24
    emplates
    0.24
    端æŃ£
    0.23
    .arm
    0.23
    ACA
    0.23
     Appalachian
    0.23
     só
    0.23
    Activations Density 0.118%

    No Known Activations