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

urator

-0.27

.mk

-0.25

ialog

-0.25

.erb

-0.24

imonial

-0.24

 roundup

-0.24

èģĶç³»

-0.23

 mars

-0.23

gne

-0.23

renom

-0.23

POSITIVE LOGITS

prev

0.28

äº²èº«

0.27

hints

0.27

è´¯ç©¿

0.25

éĢĤåĲĪèĩªå·±

0.24

termination

0.24

ä½łèĥ½

0.24

 prev

0.24

rike

0.24

ç®¡çĲĨä¸Ńå¿ĥ

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.