© 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. 24-TRANSCODER-HP
    7. 150112
    Prev
    Next
    INDEX
    Explanations

    Programming, design, and models

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è§Ĩ
    -0.30
    åĬŀ
    -0.27
    tre
    -0.26
    å²Ĺ
    -0.25
    åĤ¨
    -0.25
    Claim
    -0.25
    å¤Ħå¤Ħ
    -0.25
     vá»ĭ
    -0.25
    VERY
    -0.25
    =>'
    -0.24
    POSITIVE LOGITS
    责任åĪ¶
    0.30
     acceptance
    0.27
    çļĦè§Ĵèī²
    0.25
    æĬĹæ°§åĮĸ
    0.24
    ystone
    0.24
     perfect
    0.24
     Dad
    0.24
    åıŁ
    0.23
     affirmative
    0.23
     silicon
    0.23
    Activations Density 0.122%

    No Known Activations