© 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. 109125
    Prev
    Next
    INDEX
    Explanations

    Code/unusual language

    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
    æķĻèĤ²èµĦæºIJ
    -0.27
    .pkg
    -0.27
     cds
    -0.26
    ott
    -0.26
    ully
    -0.25
    OTT
    -0.25
    Capability
    -0.25
    vel
    -0.25
    oday
    -0.25
     pac
    -0.25
    POSITIVE LOGITS
    dress
    0.25
    olini
    0.25
    ç½ijæĺĵ
    0.25
     adjusted
    0.24
    æĪ´
    0.24
    License
    0.24
     Iss
    0.23
     '').
    0.23
    çĺ¦
    0.23
    åı³æīĭ
    0.23
    Activations Density 1.682%

    No Known Activations