© 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. 163235
    Prev
    Next
    INDEX
    Explanations

    a or an

    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
    SPAN
    -0.27
    izers
    -0.25
    ORB
    -0.25
    âĹ»
    -0.24
    åIJ¦è®¤
    -0.24
    å»ĵ
    -0.24
    绾
    -0.23
    ilio
    -0.23
     Essence
    -0.23
     phon
    -0.23
    POSITIVE LOGITS
    case
    0.28
     clas
    0.28
    entence
    0.27
    fare
    0.26
    assa
    0.26
    被æīĵ
    0.26
    rew
    0.25
     tast
    0.25
    standing
    0.25
    rese
    0.24
    Activations Density 0.002%

    No Known Activations