© 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. 163479
    Prev
    Next
    INDEX
    Explanations

    diseases

    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
    Obs
    -0.31
     Obs
    -0.29
    DataRow
    -0.27
    ded
    -0.27
     dro
    -0.27
    åĩĮ
    -0.25
    (obs
    -0.25
    å¯ħ
    -0.25
    èĪįå¾Ĺ
    -0.25
    ä¼ĺåĬ¿
    -0.25
    POSITIVE LOGITS
    .createFrom
    0.28
    ×ķ×ķ
    0.27
     keine
    0.25
    ä¸įèĥ½
    0.25
     keinen
    0.25
    å´§
    0.25
    èĽ¾
    0.25
    uada
    0.25
    olution
    0.24
    _male
    0.24
    Activations Density 0.002%

    No Known Activations