INDEX

Explanations

of

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

åľī

-0.28

èĩªèĲ¥

-0.28

 ages

-0.26

OR

-0.25

-loaded

-0.25

 Glass

-0.24

loaded

-0.24

rem

-0.24

 Globals

-0.24

ductive

-0.23

POSITIVE LOGITS

_CAST

0.27

å¦¤

0.27

ohn

0.27

ãģĹãģ¾

0.26

SenderId

0.25

_Handler

0.25

åĬĽãĤĴ

0.25

 anyway

0.24

ecome

0.23

è¶ħé«ĺ

0.23

Activations Density 0.013%

of

No Comments

No Known Activations