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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ìĭ¤

-0.26

à¹Ĥà¸ļà¸£à¸²à¸ĵ

-0.25

é¢Ī

-0.24

 Among

-0.24

Among

-0.24

 classifications

-0.24

äºĳéĽĨ

-0.24

pections

-0.24

conomic

-0.24

 shoulder

-0.24

POSITIVE LOGITS

eba

0.27

late

0.27

bang

0.26

ause

0.26

/DTD

0.25

éĩįéĩı

0.25

declar

0.24

ooks

0.24

eken

0.24

bew

0.24

Activations Density 0.017%

No Known Activations

This feature has no known activations.