INDEX

Explanations

thankfully

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

æľ¬ç½ĳç«Ļ

-0.28

<article

-0.27

èĢĮå·²

-0.26

mÃ¶glich

-0.25

-quarter

-0.25

belt

-0.25

 Honor

-0.25

æııåĨĻ

-0.24

éĢĹ

-0.23

-domain

-0.23

POSITIVE LOGITS

opot

0.28

acco

0.26

GLOBALS

0.26

apo

0.25

TR

0.25

gal

0.25

apot

0.25

aoke

0.24

robots

0.24

ylvania

0.24

Activations Density 0.005%

thankfully

No Comments

No Known Activations