INDEX

Explanations

Code/text fragments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

thest

-0.26

BERS

-0.25

estring

-0.24

irtual

-0.24

éĢł

-0.23

cope

-0.23

ssi

-0.23

 context

-0.23

å¢ĥ

-0.23

URATION

-0.22

POSITIVE LOGITS

iddles

0.26

aveled

0.25

 Ð¿ÑĢÐ¾Ð¸Ñģ

0.24

center

0.23

crc

0.23

Â«

0.23

brero

0.23

 lead

0.23

æĶ¹

0.22

over

0.22

Activations Density 0.596%

Code/text fragments

No Comments

No Known Activations