INDEX

Explanations

miscellaneous documents

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

har

-0.30

bru

-0.27

åģıå·®

-0.25

har

-0.25

 preview

-0.25

å¸

-0.25

 derivatives

-0.24

gun

-0.24

dev

-0.24

_DER

-0.24

POSITIVE LOGITS

.cd

0.27

çĽ¸å£°

0.27

InSection

0.27

ç¬¸

0.26

cd

0.25

ç»³

0.25

emble

0.24

 Heights

0.24

èĥľ

0.24

 ÑģÐ°Ð¼Ð¸

0.24

Activations Density 0.156%

miscellaneous documents

No Comments

No Known Activations