INDEX

Explanations

code

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

fono

-0.30

æ³¼

-0.28

UNU

-0.26

à¸±à¸¢

-0.26

ipy

-0.25

untime

-0.25

ellow

-0.25

krÃ¤

-0.25

iore

-0.24

_REASON

-0.24

POSITIVE LOGITS

éĢıéľ²

0.28

primaryKey

0.26

PushButton

0.24

=item

0.24

_unsigned

0.23

 BusinessException

0.23

licht

0.23

çĽĳäºĭ

0.23

 intends

0.23

 Ä°nt

0.23

Activations Density 0.009%

code

No Comments

No Known Activations