© 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. 53758
    Prev
    Next
    INDEX
    Explanations

    say

    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
    plash
    -0.27
    obby
    -0.27
    ılı
    -0.26
    chas
    -0.25
    æĪIJ年人
    -0.24
    ç¨İè´¹
    -0.23
    å¼ķãģį
    -0.23
    @media
    -0.23
    éĢĴ
    -0.23
    ared
    -0.22
    POSITIVE LOGITS
    .
    0.30
    aho
    0.27
    \.
    0.24
    å¿ĥè·³
    0.24
    cz
    0.24
    ción
    0.24
    riot
    0.24
     unity
    0.23
    çľ¼éĩĮ
    0.23
     parted
    0.23
    Activations Density 0.616%

    No Known Activations