INDEX

Explanations

research

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

arch

-0.31

 Arch

-0.30

 arch

-0.27

rch

-0.26

æĹ¶æĬ¥

-0.26

åħīæºĲ

-0.26

Arch

-0.26

 intersects

-0.25

forma

-0.24

 marched

-0.23

POSITIVE LOGITS

 defensively

0.27

HEET

0.26

ropy

0.26

äº§èĥ½

0.25

/global

0.25

Ð¿ÑĢÑı

0.25

owitz

0.24

 exponent

0.24

.offsetWidth

0.24

 globally

0.24

Activations Density 0.001%

research

No Comments

No Known Activations