INDEX

Explanations

of

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

ocate

-0.28

éĢł

-0.27

ellig

-0.27

cats

-0.27

å¹´çĶ±

-0.26

 achie

-0.25

æıı

-0.25

empl

-0.25

 ..."↵↵

-0.24

£¼

-0.24

POSITIVE LOGITS

é¹¤

0.27

/umd

0.26

ime

0.26

anke

0.26

udios

0.24

 courses

0.24

IME

0.24

fter

0.24

aad

0.24

 Ibid

0.24

Activations Density 0.004%

of

No Comments

No Known Activations