© 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. 162496
    Prev
    Next
    INDEX
    Explanations

    .wikipedia

    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
     pity
    -0.26
    culo
    -0.26
     handed
    -0.26
     CWE
    -0.26
    )y
    -0.25
    rolley
    -0.24
    -central
    -0.24
     Courier
    -0.24
     fooled
    -0.24
    fos
    -0.23
    POSITIVE LOGITS
    arith
    0.28
    existing
    0.28
    existent
    0.27
    olin
    0.27
    loth
    0.27
    votes
    0.26
    navigate
    0.26
    Joint
    0.25
    imat
    0.25
     implications
    0.24
    Activations Density 0.010%

    No Known Activations