© 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. 162427
    Prev
    Next
    INDEX
    Explanations

    thinks

    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
     yourselves
    -0.27
     optical
    -0.26
     grant
    -0.26
     Fran
    -0.26
     Hydraulic
    -0.25
    äºĨä¸Ģåľº
    -0.25
     attribution
    -0.25
    éī´å®ļ
    -0.24
    å¸ĤæķĻèĤ²
    -0.24
    /current
    -0.24
    POSITIVE LOGITS
    æĥ³åĪ°
    0.72
    æĥ³åĪ°äºĨ
    0.52
    èģĶ
    0.47
    æĥ³èµ·
    0.43
     think
    0.41
    èģĶæĥ³
    0.41
    æĥ³èµ·äºĨ
    0.41
    èĦijæµ·ä¸Ń
    0.40
    think
    0.40
    Think
    0.39
    Activations Density 0.001%

    No Known Activations