© 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. 162793
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĭ¬
    -0.30
    _BUSY
    -0.26
     paren
    -0.26
    *č↵
    -0.25
    неÑģен
    -0.25
    ]*(
    -0.24
    éĢı
    -0.24
    åĪĴ
    -0.24
     masking
    -0.24
    						č↵
    -0.23
    POSITIVE LOGITS
    iform
    0.26
    æĹĥ
    0.25
    yl
    0.24
    enerate
    0.23
    gether
    0.23
    æĶ¶çĽĬ
    0.23
    驱
    0.23
    æ°¸ä¹ħ
    0.22
    илÑĮ
    0.22
    -associated
    0.22
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.