INDEX

Explanations

te

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

MARK

-0.27

 marker

-0.27

assin

-0.26

marker

-0.25

erving

-0.25

.marker

-0.25

signals

-0.25

ÑĳÑĢ

-0.25

arth

-0.24

 markers

-0.24

POSITIVE LOGITS

çļ®

0.29

enne

0.28

acular

0.27

æ»¡

0.26

ä¸įåı¯

0.26

ÅĽÄĩ

0.26

 abstract

0.24

çĥĽ

0.24

æīĭä¸ŃçļĦ

0.24

gon

0.24

Activations Density 0.788%

te

No Comments

No Known Activations