© 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. 163430
    Prev
    Next
    INDEX
    Explanations

    crystal

    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
     Aud
    -0.30
    é¼»
    -0.28
    主æĿĥ
    -0.27
    stad
    -0.26
     sew
    -0.25
    uden
    -0.24
    sense
    -0.24
    imas
    -0.24
    scheme
    -0.24
    sip
    -0.23
    POSITIVE LOGITS
     crystal
    0.32
    ization
    0.32
     distribution
    0.29
    atic
    0.28
    ation
    0.28
    Crystal
    0.27
    ous
    0.27
     Me
    0.27
    ized
    0.27
     formation
    0.27
    Activations Density 0.139%

    No Known Activations