© 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. 162681
    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
     proposal
    -0.28
    迹
    -0.28
    æİ¥ç§į
    -0.28
     earliest
    -0.27
     sle
    -0.26
    æİ¥
    -0.26
    æıIJåĩºçļĦ
    -0.26
     discharged
    -0.26
     proposals
    -0.26
     assembled
    -0.26
    POSITIVE LOGITS
    ivr
    0.29
    izzare
    0.27
    å½Ĺ
    0.27
    åħ°èĬ±
    0.26
    BAT
    0.25
    èĻİ
    0.25
    AAD
    0.25
     bells
    0.24
    /apple
    0.24
    èĬ±
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.