INDEX

Explanations

numbers

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

did

-0.27

monds

-0.26

iams

-0.24

 fully

-0.24

åĲįé¢Ŀ

-0.23

éĩľ

-0.23

ÑĢÑĥ

-0.23

ÑıÐ¼

-0.23

 Transition

-0.23

wald

-0.23

POSITIVE LOGITS

ZZ

0.27

çĪĨåıĳ

0.27

åıĺäºĨ

0.26

å¾Ĺå¤©çĭ¬åİļ

0.26

èľľ

0.26

dden

0.25

åīĶ

0.25

ZZ

0.24

 promot

0.24

 blat

0.24

Activations Density 0.001%

numbers

No Comments

No Known Activations