© 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. 162802
    Prev
    Next
    INDEX
    Explanations

    here

    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
    @qq
    -0.27
    otec
    -0.26
    ')+
    -0.25
    ','=',
    -0.24
    .gl
    -0.23
    eba
    -0.23
    责任åĪ¶
    -0.23
    å¹
    -0.23
    åĩ¡æĺ¯
    -0.23
    çįIJ
    -0.23
    POSITIVE LOGITS
    https
    0.33
    :http
    0.32
     https
    0.32
     here
    0.31
    è¿ĻéĩĮ
    0.30
    æѤå¤Ħ
    0.30
    http
    0.29
    here
    0.29
    ãģĵãģ¡ãĤī
    0.29
     http
    0.28
    Activations Density 0.008%

    No Known Activations