© 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. 32-TRANSCODER-HP
    7. 41625
    Prev
    Next
    INDEX
    Explanations

    say "ending -third"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬ¨æĢģ
    -0.29
     dynamic
    -0.26
    incl
    -0.25
     Bold
    -0.25
    ä¸ĸ
    -0.25
    FA
    -0.24
    åij¨æľŁ
    -0.24
    ä»»æľŁ
    -0.24
     ov
    -0.24
    abor
    -0.23
    POSITIVE LOGITS
    åĽĽ
    0.35
     percentage
    0.34
    äºĶ
    0.33
    five
    0.32
     fifth
    0.32
     five
    0.31
    allet
    0.31
    -five
    0.30
    çĻ¾åĪĨ
    0.28
    åįģ
    0.28
    Activations Density 0.001%

    No Known Activations