© 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. 162400
    Prev
    Next
    INDEX
    Explanations

    Instructions/Steps

    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
    å¾Īå¿«å°±
    -0.30
    åĪĻ
    -0.28
    	then
    -0.27
    è¤Ĵ
    -0.27
    Narrated
    -0.27
     CPF
    -0.27
    ppv
    -0.26
     then
    -0.26
    PFN
    -0.25
    creativecommons
    -0.25
    POSITIVE LOGITS
     substitutions
    0.29
    ä¸īæĺ¯
    0.26
    culus
    0.26
    éĹªåħī
    0.25
    åħį
    0.25
    ãĥ¼ãĥ³
    0.25
    utations
    0.25
    sc
    0.25
    å¤ĩçĶ¨
    0.25
     substitution
    0.24
    Activations Density 0.006%

    No Known Activations