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

ä¸ĢåĪ»

-0.28

.ProgressBar

-0.28

 provisioning

-0.27

à¹Īà¸²à¸¢

-0.27

çĮĽ

-0.25

 bootstrap

-0.25

 Provision

-0.24

 chrome

-0.24

 *----------------------------------------------------------------

-0.24

 prÃ³

-0.23

POSITIVE LOGITS

shaw

0.25

icy

0.25

 Functions

0.24

Ø¯Ø¯

0.24

_functions

0.24

datal

0.24

erton

0.23

translator

0.23

cker

0.23

yped

0.23

Activations Density 0.071%

No Known Activations

This feature has no known activations.