© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162935
    Prev
    Next
    INDEX
    Explanations

    Narrative/descriptive text

    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
    å»¶æľŁ
    -0.30
    ä»įæľī
    -0.28
    éĶ²
    -0.26
    _refer
    -0.26
    Still
    -0.25
    è¿ĺæĺ¯
    -0.25
    ä»įçĦ¶æĺ¯
    -0.25
     Weiner
    -0.25
    ä»įçĦ¶
    -0.25
    maf
    -0.24
    POSITIVE LOGITS
    åį¡
    0.30
    :";č↵
    0.26
    ideal
    0.25
    á»Ĺi
    0.25
     tie
    0.25
    çIJĨæĥ³
    0.25
    ections
    0.25
    ection
    0.25
    çīĻ
    0.23
    ÑĢÑıд
    0.23
    Activations Density 0.004%

    No Known Activations