INDEX

Explanations

.,

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÃŃf

-0.32

çĺŁ

-0.26

æ§Ĭ

-0.25

dc

-0.25

pen

-0.24

çĮĿ

-0.24

 pellet

-0.24

 swath

-0.24

çķ¹

-0.24

 chute

-0.23

POSITIVE LOGITS

åģ¥åº·

0.32

åģ¥

0.28

utive

0.28

 Psychic

0.27

 render

0.26

Live

0.26

å¨ĺ

0.26

å®īåº·

0.25

licative

0.25

èº«å¿ĥåģ¥åº·

0.25

Activations Density 0.000%

.,

No Comments

No Known Activations