© 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. 163296
    Prev
    Next
    INDEX
    Explanations

    diverse text excerpts

    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
    空
    -0.27
    çĶŁæĦı
    -0.26
    âĦľ
    -0.25
     differentiated
    -0.25
    Ļ¶
    -0.25
    ãĤ¹ãĤŃ
    -0.24
     expressed
    -0.24
    `č↵
    -0.23
    触åıĬ
    -0.23
    UFF
    -0.23
    POSITIVE LOGITS
     by
    0.46
    by
    0.40
     oleh
    0.40
     bợi
    0.39
    çĶ±
    0.39
    _by
    0.34
    By
    0.32
    ByUrl
    0.32
    byname
    0.31
    BY
    0.31
    Activations Density 0.010%

    No Known Activations