© 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. 33-TRANSCODER-HP
    7. 53023
    Prev
    Next
    INDEX
    Explanations

    technical/foreign text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLE
    -0.26
     ev
    -0.26
    æľĢéļ¾
    -0.25
    éļ¾
    -0.24
     lr
    -0.24
     jsonResponse
    -0.24
    Pick
    -0.24
    isses
    -0.23
     sca
    -0.23
    SHOW
    -0.23
    POSITIVE LOGITS
    resh
    0.29
     mortal
    0.26
    æ¡ħ
    0.26
     radix
    0.25
     interfering
    0.25
    çĵ¯
    0.24
    å¤Ļ
    0.24
    ammable
    0.24
    paring
    0.24
    å¤©åľ°
    0.24
    Activations Density 0.005%

    No Known Activations