© 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. 25-TRANSCODER-HP
    7. 107821
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.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
    -0.31
    dens
    -0.29
     outr
    -0.28
    æıIJåįĩäºĨ
    -0.28
    repid
    -0.27
    èĢģ乡
    -0.26
    åħ³å¿ĥ
    -0.25
    aniu
    -0.25
    çŁ¥æĥħ
    -0.25
     neglig
    -0.24
    POSITIVE LOGITS
     forks
    0.32
     Fork
    0.28
    åĬĥ
    0.28
    fork
    0.27
    åĪĴ
    0.26
     Ava
    0.25
     fork
    0.25
    åıī
    0.25
    ungi
    0.25
    ulk
    0.25
    Activations Density 0.115%

    No Known Activations