INDEX

Explanations

standalone

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 coll

-0.30

coll

-0.28

 cond

-0.28

è²łãģĳ

-0.27

.Tx

-0.27

ILED

-0.26

çĽĺçĤ¹

-0.26

èŀį

-0.25

åĪĩ

-0.25

 slices

-0.25

POSITIVE LOGITS

laz

0.28

åıĳçĥ§

0.27

åħ¬

0.25

ä½ķå¿ħ

0.25

boxed

0.24

Ð»Ð¸Ð±Ð¾

0.24

çĨŁæĤī

0.24

æ®Ĩ

0.24

 Ð»Ð¸

0.24

æ¦

0.24

Activations Density 0.005%

standalone

No Comments

No Known Activations