© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 94
    Prev
    Next
    INDEX
    Explanations

    Glaciers and geography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iggins
    -0.25
    å¾ĭå¸ĪäºĭåĬ¡
    -0.25
    ÑĦеÑģÑģ
    -0.25
     &_
    -0.24
    esthes
    -0.24
     booming
    -0.24
    -purpose
    -0.24
    omba
    -0.24
    -pos
    -0.24
    poser
    -0.23
    POSITIVE LOGITS
    æī£
    0.28
    ices
    0.27
     каÑĤал
    0.25
     peça
    0.25
    åĪĹ
    0.25
    edm
    0.25
     slippery
    0.24
    è°ı
    0.24
     prem
    0.24
    /archive
    0.24
    Activations Density 0.027%

    No Known Activations