INDEX

Explanations

aluminum

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

iquid

-0.27

åħŃåĲĪ

-0.27

åĬłè½½

-0.26

å²ļ

-0.26

 loading

-0.26

 aluminium

-0.25

è£¨

-0.25

azer

-0.25

 amongst

-0.24

Ð¸Ð½Ñĭ

-0.24

POSITIVE LOGITS

clair

0.30

abella

0.28

è¾ŀ

0.28

ropol

0.27

ropolis

0.27

robat

0.26

_zip

0.25

é¼ĵ

0.25

wed

0.24

gtest

0.24

Activations Density 0.160%

aluminum

No Comments

No Known Activations