© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97414
    Prev
    Next
    INDEX
    Explanations

    Complete sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    认
    -0.27
    owo
    -0.26
     fortn
    -0.26
    æķıéĶIJ
    -0.25
    ANDLE
    -0.25
    念
    -0.25
    stripe
    -0.24
    NBC
    -0.24
    adam
    -0.24
    alf
    -0.24
    POSITIVE LOGITS
     enough
    0.33
    oyer
    0.31
    äºĨ大éĩıçļĦ
    0.29
    满满çļĦ
    0.26
    ummies
    0.26
    è¶³å¤Ł
    0.25
    æĹłéĻIJ
    0.25
    RAR
    0.25
     por
    0.25
     busy
    0.25
    Activations Density 0.012%

    No Known Activations