© 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. 163238
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    åı£
    -0.30
     dried
    -0.27
    èıľ
    -0.26
    ker
    -0.26
     Mess
    -0.26
    åijĪçİ°
    -0.25
    ickle
    -0.25
     glob
    -0.25
    CALE
    -0.25
     Norman
    -0.24
    POSITIVE LOGITS
    è¿IJç®Ĺ
    0.40
     concaten
    0.39
     operator
    0.36
     subtraction
    0.36
     concatenate
    0.35
     multiplication
    0.34
     operators
    0.34
    concat
    0.34
     oper
    0.34
     operand
    0.33
    Activations Density 0.041%

    No Known Activations