© 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. 53469
    Prev
    Next
    INDEX
    Explanations

    code/filenames

    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
    ected
    -0.27
    ä½Ļ
    -0.26
    udder
    -0.25
    è
    -0.25
    åı¤
    -0.25
    olding
    -0.25
    åĪ»
    -0.25
    æľīæ¯Ĵ
    -0.24
    åIJīåĪ©
    -0.24
     Butter
    -0.24
    POSITIVE LOGITS
    .af
    0.29
    Lens
    0.29
    fef
    0.29
    инÑĦ
    0.28
    lemn
    0.27
    unity
    0.27
    .uf
    0.27
    ufs
    0.27
    spb
    0.27
    ÙĪد
    0.26
    Activations Density 0.009%

    No Known Activations