© 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. 163397
    Prev
    Next
    INDEX
    Explanations

    business and technology

    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
     patterns
    -0.26
     ActionTypes
    -0.25
    stell
    -0.25
    Behaviour
    -0.25
    åĬ¨ä½ľ
    -0.25
     resolutions
    -0.24
    å±ĬæŶ
    -0.24
    ÑĨов
    -0.24
     policemen
    -0.24
     Patterns
    -0.23
    POSITIVE LOGITS
     platform
    0.28
    PLATFORM
    0.26
    avern
    0.26
    èĪIJ
    0.26
    ",{
    0.26
    ',{
    0.26
    .foundation
    0.26
    ês
    0.25
     Platform
    0.25
    ",&
    0.25
    Activations Density 0.083%

    No Known Activations