INDEX

Explanations

a pattern it never finds here; it appears to be a silent/inactive neuron with no detectable triggers.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ponder

-0.30

ihar

-0.26

zap

-0.25

Osw

-0.25

zas

-0.24

isel

-0.24

ovation

-0.24

 Emin

-0.24

 theirs

-0.24

ç»¿èī²éĢļéģĵ

-0.24

POSITIVE LOGITS

Ty

0.27

toy

0.27

 bour

0.26

ascii

0.26

 scept

0.25

Jr

0.24

)section

0.24

ç¬¬ä¸īèĬĤ

0.24

æĪ¾

0.24

nee

0.24

Activations Density 41.548%

No Known Activations

This feature has no known activations.