INDEX

Explanations

-day

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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¨Ĺ

-0.26

foon

-0.24

ifix

-0.24

 Prim

-0.24

åı¯èĥ½åŃĺåľ¨

-0.24

æļ¹

-0.24

(serializer

-0.24

 reluct

-0.23

exh

-0.23

Fax

-0.23

POSITIVE LOGITS

tribute

0.27

åĵģ

0.25

 pillows

0.25

getDrawable

0.25

æģ¶æĢ§

0.24

 sweep

0.24

IFS

0.24

 interpolate

0.24

weed

0.24

UILT

0.23

Activations Density 0.019%

-day

No Comments

No Known Activations