INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yne

-0.26

ington

-0.26

äº¨

-0.26

conut

-0.26

åħį

-0.25

çĪ½

-0.25

çľł

-0.25

drink

-0.24

quete

-0.24

ytic

-0.24

POSITIVE LOGITS

mission

0.26

...</

0.25

ius

0.25

 greetings

0.25

LEV

0.25

èĢ§

0.24

 boundaries

0.24

...]↵↵

0.24

è¾¹çķĮ

0.24

 boundary

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.