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

 even

-0.27

å¾®å¦Ļ

-0.27

bay

-0.26

å¤§åľ°

-0.25

Bay

-0.25

åħ¼

-0.25

drawing

-0.25

 drawing

-0.25

åµĮ

-0.25

Emb

-0.25

POSITIVE LOGITS

glas

0.29

ilded

0.26

ansk

0.25

çŃĽ

0.25

edy

0.24

Ð¸ÑĤÐµÐ»ÐµÐ¹

0.24

_taxonomy

0.24

-dom

0.24

ä¾§

0.23

_domains

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.