© 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. 23-TRANSCODER-HP
    7. 24218
    Prev
    Next
    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃĹä½ĵ
    -0.24
     różne
    -0.24
     Birth
    -0.24
    нÑĥÑĤ
    -0.24
    马桶
    -0.23
    çĽ¡
    -0.23
    .getMap
    -0.23
    驼
    -0.23
    urse
    -0.23
    umpy
    -0.23
    POSITIVE LOGITS
     key
    0.36
    çļĦåīįæıIJ
    0.34
     challenge
    0.31
     part
    0.30
     problem
    0.30
    åīįæıIJæĺ¯
    0.29
     issue
    0.29
     concern
    0.29
    éĹ®é¢ĺæĺ¯
    0.29
     reason
    0.28
    Activations Density 0.009%

    No Known Activations