INDEX

Explanations

nineteen

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 parking

-0.27

 respective

-0.26

ä¼Ĺå¤ļ

-0.25

åİ²

-0.25

å¹ķåĲİ

-0.25

 Preserve

-0.24

 Trail

-0.24

 overload

-0.24

ve

-0.24

POSITIVE LOGITS

strand

0.29

gba

0.27

AGES

0.26

çļĦèĢģ

0.25

.dex

0.25

nex

0.24

itty

0.24

stk

0.24

shima

0.24

yx

0.24

Activations Density 0.002%

nineteen

No Comments

No Known Activations