© 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. 23-TRANSCODER-HP
    7. 24030
    Prev
    Next
    INDEX
    Explanations

    Similarity and magnitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.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°¤åħ¶æĺ¯
    -0.29
     vi
    -0.28
    onnen
    -0.25
    åĪĩåī²
    -0.25
    ulant
    -0.24
    åĭŁ
    -0.24
     admit
    -0.24
    rais
    -0.24
    obil
    -0.23
    TODO
    -0.23
    POSITIVE LOGITS
     ones
    0.27
     ours
    0.27
     finest
    0.26
     yours
    0.25
     theirs
    0.24
    ityEngine
    0.24
     Gallagher
    0.24
    æŁľåı°
    0.24
     legislature
    0.24
    particles
    0.23
    Activations Density 0.017%

    No Known Activations