© 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. 162984
    Prev
    Next
    INDEX
    Explanations

    steady

    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
    s
    -0.37
    sist
    -0.31
    sy
    -0.28
    sites
    -0.28
    sad
    -0.27
     specialised
    -0.27
    spect
    -0.26
    ilinear
    -0.26
    suspend
    -0.26
    ledged
    -0.25
    POSITIVE LOGITS
    ness
    0.30
     enough
    0.25
    -ish
    0.25
    ãģª
    0.24
     train
    0.24
    -per
    0.24
    acci
    0.24
    åıijçĥ§
    0.23
    eing
    0.23
    éļıçĿĢæŶéĹ´
    0.23
    Activations Density 0.291%

    No Known Activations