© 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. 163808
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ÑijÑĤ
    -0.33
    reated
    -0.27
    eric
    -0.26
    ’Brien
    -0.26
    еÑģÑĤво
    -0.25
     ticket
    -0.25
    oure
    -0.24
    tering
    -0.24
    ombre
    -0.24
    ieder
    -0.24
    POSITIVE LOGITS
    pend
    0.27
    è¿Ļä¸įæĺ¯
    0.26
    ÑĥÑĪ
    0.25
    agua
    0.24
     Desert
    0.24
    room
    0.24
    æ£ĭ
    0.24
    æīįèĥ½å¤Ł
    0.24
     Legends
    0.24
    ìŀħ
    0.24
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.