© 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. 24743
    Prev
    Next
    INDEX
    Explanations

    Programming questions/solutions

    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
    ä»ĸ们éĥ½
    -0.28
    "):č↵
    -0.28
    åIJĮæĻĤãģ«
    -0.28
    eid
    -0.26
    _capability
    -0.26
    talk
    -0.25
    )="
    -0.24
    å½ĵä¹ĭ
    -0.24
     sophistic
    -0.24
    )m
    -0.24
    POSITIVE LOGITS
     Dil
    0.35
     Hol
    0.29
    плав
    0.29
    Manifest
    0.27
     Suite
    0.26
    ↵↵↵
    0.25
     dil
    0.25
     Everything
    0.25
    Overview
    0.25
    åĪĴ
    0.25
    Activations Density 0.002%

    No Known Activations