© 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. 162449
    Prev
    Next
    INDEX
    Explanations

    Negative situations and possibilities

    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
    eer
    -0.28
    iete
    -0.26
    /browse
    -0.26
     slain
    -0.25
    è´¢çī©
    -0.24
    наÑĤ
    -0.24
    /WebAPI
    -0.23
    lete
    -0.23
    åıªçŁ¥éģĵ
    -0.23
     defer
    -0.23
    POSITIVE LOGITS
     unlikely
    0.64
    unlikely
    0.57
    åı¯èĥ½æĢ§
    0.55
    çļĦåı¯èĥ½æĢ§
    0.53
     rare
    0.52
    æ¦Ĥçİĩ
    0.50
     likelihood
    0.50
     occurrence
    0.49
     improbable
    0.48
    åıijçĶŁ
    0.48
    Activations Density 0.005%

    No Known Activations