© 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. 23-TRANSCODER-HP
    7. 162069
    Prev
    Next
    INDEX
    Explanations

    pol

    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
     either
    -0.35
    è¦ģä¹Ī
    -0.35
    either
    -0.31
    æĹłè®ºæĺ¯
    -0.27
    åĩłä½į
    -0.27
    åĪĨåĪ«æĺ¯
    -0.26
     Icons
    -0.26
    åĩłç§į
    -0.25
    åŁºå±Ĥ
    -0.25
    inq
    -0.25
    POSITIVE LOGITS
    ãĤ¯ãĥĪ
    0.29
    quat
    0.25
    è°¬
    0.24
    .minecraft
    0.24
     khoá
    0.23
    åį¡è½¦
    0.23
    åĽ½éģĵ
    0.23
    ANCEL
    0.23
    çĹ£
    0.23
     ferr
    0.23
    Activations Density 0.002%

    No Known Activations