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

æ®ĸ

-0.31

(Properties

-0.28

ike

-0.28

yet

-0.28

 base

-0.26

 BaseService

-0.26

ann

-0.25

 duro

-0.25

nez

-0.25

 drip

-0.25

POSITIVE LOGITS

ATHER

0.27

æ¿ł

0.25

 foresee

0.25

_SEGMENT

0.25

 manh

0.25

;break

0.24

edelta

0.24

agem

0.24

-character

0.24

Segment

0.24

Activations Density 0.007%

No Known Activations

This feature has no known activations.