© 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. 130129
    Prev
    Next
    INDEX
    Explanations

    hyphens and dashes

    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
    èĹIJ
    -0.31
    gest
    -0.28
    option
    -0.27
    arrants
    -0.26
     Nich
    -0.23
    ðĿĻ½
    -0.23
    为ä»Ģä¹Ī
    -0.23
    alle
    -0.23
    getOption
    -0.22
    NewLabel
    -0.22
    POSITIVE LOGITS
    cip
    0.28
     pseud
    0.26
    abet
    0.25
    å°Ŀ
    0.25
    viz
    0.24
    enze
    0.24
    å¯Ħ
    0.24
     Kane
    0.24
    çĨŁ
    0.24
     imagined
    0.23
    Activations Density 0.008%

    No Known Activations