INDEX

Explanations

organizations or places

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

Ð°ÑĤÐ¾ÑĢ

-0.26

_bt

-0.26

éĶ°

-0.26

WEST

-0.25

(attr

-0.24

-Smith

-0.24

west

-0.24

ÙģÙĩÙħ

-0.24

(dp

-0.24

ows

-0.24

POSITIVE LOGITS

imitive

0.28

éħįå¥Ĺ

0.26

åİŁ

0.26

 supper

0.26

åħ³åĪĩ

0.25

sed

0.25

æĪĳä»¬ä¹Ł

0.24

 prior

0.24

ÙĨÙĬØ©

0.24

inding

0.24

Activations Density 0.002%

organizations or places

No Comments

No Known Activations