© 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. 22-TRANSCODER-HP
    7. 111790
    Prev
    Next
    INDEX
    Explanations

    Biological classifications/species

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¢ħ
    -0.29
    ubo
    -0.28
    ordo
    -0.24
    uld
    -0.24
    olicit
    -0.24
    ä½ĵè´´
    -0.24
    รม
    -0.23
    isters
    -0.23
    çħŀ
    -0.23
     debounce
    -0.23
    POSITIVE LOGITS
    çĦ¶
    0.28
    enci
    0.28
    ably
    0.27
    Ñįн
    0.26
     scor
    0.25
    æĥľ
    0.24
    æĥł
    0.24
    yt
    0.24
    å¼ĥ
    0.24
    ensen
    0.23
    Activations Density 0.033%

    No Known Activations