INDEX

Explanations

line

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

Second

-0.33

 Second

-0.32

 second

-0.27

young

-0.27

Expected

-0.27

rip

-0.26

_second

-0.26

 perm

-0.25

 Young

-0.25

 soul

-0.25

POSITIVE LOGITS

 AsyncStorage

0.26

ÑĩÑĮ

0.25

Ð»ÑıÐµÐ¼

0.25

{_

0.25

ellery

0.25

raises

0.25

 redux

0.24

%f

0.24

Ã¦re

0.24

å¥¢ä¾Ī

0.24

Activations Density 0.001%

line

No Comments

No Known Activations