© 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. 54384
    Prev
    Next
    INDEX
    Explanations

    che

    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
    ion
    -0.30
    iy
    -0.24
    ogy
    -0.24
    asca
    -0.24
    oc
    -0.24
    ycles
    -0.24
    prop
    -0.24
    yaw
    -0.24
    xf
    -0.24
    ɲ
    -0.24
    POSITIVE LOGITS
    æ¤Ĵ
    0.32
     wik
    0.29
    Inspect
    0.28
    adata
    0.28
    åĴª
    0.27
    èĮĥ
    0.24
    æĹłæīĢ
    0.24
    ç½ij讯
    0.24
    inspect
    0.24
    寮
    0.24
    Activations Density 0.007%

    No Known Activations