© 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. 162463
    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
    passes
    -0.28
    æĹłå¿§
    -0.26
     Happ
    -0.26
    еÑĢи
    -0.26
    iny
    -0.25
    å®īåħ¨æĦŁ
    -0.25
    оÑģÑĤи
    -0.25
     happens
    -0.25
    ere
    -0.25
    .toObject
    -0.25
    POSITIVE LOGITS
    odate
    0.29
    å°Ī家
    0.26
    åģļ人
    0.26
    ++;č↵
    0.25
    èĤĩ
    0.25
    agrams
    0.24
    	progress
    0.24
    æįķ
    0.24
     expert
    0.24
    ++;↵↵
    0.24
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.