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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162452
    Prev
    Next
    INDEX
    Explanations

    1

    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
    elight
    -0.30
    åįĬ个
    -0.29
    ourd
    -0.27
    å¤ĩåıĹ
    -0.26
    ÑĩаÑĤ
    -0.26
    orrent
    -0.26
    cé
    -0.25
    esome
    -0.25
    ynn
    -0.24
    åĢĴ
    -0.24
    POSITIVE LOGITS
    缱
    0.26
    اÙģ
    0.26
    {%
    0.25
    ãĤ¿ãĥ«
    0.25
     `{
    0.25
    ç»Ļ她
    0.24
    æį§
    0.24
    EEDED
    0.24
    彪
    0.24
    kwargs
    0.24
    Activations Density 0.006%

    No Known Activations