INDEX

Explanations

balancing/counteracting

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

tk

-0.28

stood

-0.27

lib

-0.26

 canc

-0.25

 CancellationToken

-0.25

èµ°åĩºæĿ¥

-0.25

åıĳå±ķæĪĺçķ¥

-0.25

åŃĲå¼¹

-0.25

ava

-0.24

ibt

-0.24

POSITIVE LOGITS

æ¨¡

0.27

;q

0.26

åıªæľī

0.26

alÄ±k

0.25

ä¾ĽéľĢ

0.24

rieve

0.23

Ø§ÙĪÙĬØ©

0.23

 Ð½Ð¸Ðº

0.23

<Func

0.23

itizen

0.23

Activations Density 0.054%

balancing/counteracting

No Comments

No Known Activations