INDEX

Explanations

carrier augmented

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

è¿ĳ

-0.26

COVID

-0.26

Close

-0.26

omorphic

-0.25

 near

-0.25

plash

-0.25

zap

-0.25

 similar

-0.25

 overt

-0.25

-0.24

POSITIVE LOGITS

idia

0.27

ition

0.25

nym

0.24

ialized

0.24

ction

0.24

ÙħÙĪØ±

0.24

vig

0.24

lessly

0.24

_RTC

0.24

hid

0.24

Activations Density 0.005%

carrier augmented

No Comments

No Known Activations