INDEX

Explanations

Totality or general statements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RefPtr

-0.29

izedName

-0.27

éĢĲ

-0.27

ä½ıäºĨ

-0.27

standing

-0.26

è¯´çļĦæĺ¯

-0.26

 dign

-0.25

ling

-0.24

vertise

-0.24

bjerg

-0.24

POSITIVE LOGITS

 Resp

0.28

Resp

0.26

åĬŁ

0.26

 Responses

0.25

RESP

0.25

responses

0.25

IU

0.25

èĢģåŃĲ

0.24

Ã¶lÃ¼

0.24

sembler

0.24

Activations Density 0.012%

Totality or general statements

No Comments

No Known Activations