INDEX

Explanations

No Explanations Found

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

friendly

-0.29

riendly

-0.28

èį¡

-0.27

 Friendly

-0.26

"bytes

-0.26

 Scho

-0.25

ried

-0.25

éħµ

-0.24

.appspot

-0.24

igest

-0.24

POSITIVE LOGITS

sand

0.27

åĲĦå¼ı

0.27

sit

0.26

VS

0.26

abh

0.24

ÑĤÐ¾Ð¿

0.24

ä¹Ŀå¤§

0.24

çļĦæ¯ĶèµĽ

0.24

 narr

0.23

ockey

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.