© 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. 162892
    Prev
    Next
    INDEX
    Explanations

    gatherings of people

    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
    ä¸ĢæĶ¯
    -0.28
    åĽ½å®¶éĺŁ
    -0.27
    á»įng
    -0.26
     veter
    -0.26
    ion
    -0.26
    thers
    -0.26
    ergus
    -0.26
    arsers
    -0.25
     dn
    -0.25
    ioned
    -0.25
    POSITIVE LOGITS
    åĩºåıij
    0.27
    åī
    0.26
    å½ĵ天
    0.26
    çĤ³
    0.25
    pf
    0.25
     altern
    0.24
    achen
    0.24
    å½ĵæĻļ
    0.24
    Altern
    0.24
    ifi
    0.23
    Activations Density 0.009%

    No Known Activations