INDEX

Explanations

Beau

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

ifax

-0.28

(SP

-0.27

isp

-0.27

è¿ĺä»¥ä¸º

-0.26

ymi

-0.25

æ³¢åĬ¨

-0.25

[](

-0.24

eways

-0.24

ÃŃst

-0.24

peng

-0.24

POSITIVE LOGITS

Judge

0.27

ued

0.26

uable

0.26

tails

0.25

.omg

0.24

Ð¿Ð°ÑĢ

0.24

PDO

0.24

judge

0.24

çļĦçĶŁåĳ½

0.24

 Marion

0.24

Activations Density 0.920%

Beau

No Comments

No Known Activations