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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98658
    Prev
    Next
    INDEX
    Explanations

    accept

    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
    èģĬ
    -0.25
    æ·±å¤Ħ
    -0.25
    depth
    -0.25
    æ·±å±Ĥ
    -0.25
     bald
    -0.24
    axios
    -0.24
    activated
    -0.23
    contract
    -0.23
     quê
    -0.23
     depths
    -0.23
    POSITIVE LOGITS
    nowled
    0.29
    绶
    0.27
     recognizing
    0.26
    ermann
    0.26
     recognize
    0.25
    prm
    0.24
    ltr
    0.23
     recognized
    0.23
    ilog
    0.23
    venida
    0.22
    Activations Density 0.224%

    No Known Activations