INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 readings

-0.28

ivable

-0.26

 pans

-0.26

 Mund

-0.24

ä¹ĺè½¦

-0.24

 --↵

-0.24

.getLogin

-0.24

oreach

-0.24

ikh

-0.23

º«

-0.23

POSITIVE LOGITS

äººä¸º

0.32

mist

0.29

ellig

0.28

éĢĤåĲĪ

0.26

rence

0.25

rica

0.25

Tul

0.25

arest

0.25

hsi

0.25

apest

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.