© 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. 32-TRANSCODER-HP
    7. 41806
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    miÅŁ
    -0.29
    ç°¿
    -0.28
     pairwise
    -0.28
    ä¹İ
    -0.28
    å®ĺæĸ¹å¾®åįļ
    -0.27
    楼主
    -0.26
    çĴľ
    -0.26
     that
    -0.25
    ours
    -0.25
     theirs
    -0.24
    POSITIVE LOGITS
     The
    0.42
    -The
    0.34
     Then
    0.33
     While
    0.32
     First
    0.32
    The
    0.32
    First
    0.30
    _first
    0.30
    	The
    0.29
     Since
    0.29
    Activations Density 0.001%

    No Known Activations