© 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
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 163518
    Prev
    Next
    INDEX
    Explanations

    help requests

    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
    igte
    -0.28
    çĸ¡
    -0.28
    UnitTest
    -0.27
    achine
    -0.27
    lename
    -0.26
    .lab
    -0.25
    Ctr
    -0.25
    úb
    -0.25
    溯
    -0.24
    æĪ·ç±į
    -0.24
    POSITIVE LOGITS
     alone
    0.27
    Traits
    0.26
     Vocabulary
    0.25
     TCL
    0.25
     favoured
    0.25
     Offers
    0.25
     specialised
    0.25
    æģ°å½ĵ
    0.25
    æķ´æĶ¹æİªæĸ½
    0.24
     offered
    0.24
    Activations Density 0.008%

    No Known Activations