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

KNOWN

-0.27

èĥļ

-0.27

 minors

-0.26

çļĦå¯¹è±¡

-0.26

rollo

-0.26

ToPoint

-0.25

ctor

-0.25

_MA

-0.25

liers

-0.24

ctors

-0.24

POSITIVE LOGITS

ounced

0.27

uch

0.26

 pencil

0.26

ouch

0.26

Don

0.25

.getLogger

0.24

Hog

0.24

 manifest

0.24

manifest

0.24

è§ĩ

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.