INDEX

Explanations

risk

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

æĭĽ

-0.28

gin

-0.26

 ÑģÐ¿ÑĢÐ°Ð²

-0.26

åı«æĪĳ

-0.25

amen

-0.25

ä¿®å£«

-0.25

çĶĺ

-0.25

åĹ½

-0.25

uating

-0.24

 Initi

-0.24

POSITIVE LOGITS

CAT

0.27

LTR

0.26

Dyn

0.26

iets

0.25

 Catal

0.25

 format

0.24

 prac

0.24

Dyn

0.24

otty

0.24

	Destroy

0.23

Activations Density 0.003%

risk

No Comments

No Known Activations