INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 treat

-0.30

 vern

-0.27

 known

-0.27

 bust

-0.27

icon

-0.26

ev

-0.25

 treated

-0.25

 strapped

-0.25

åľ¨åĽ½åĨħ

-0.25

å¥ĩ

-0.25

POSITIVE LOGITS

èĲ¥

0.28

antar

0.27

[code

0.27

-channel

0.27

 Programmer

0.26

cosa

0.26

æ²ī

0.25

abouts

0.25

æĶ¿åºľ

0.25

ora

0.25

Activations Density 6.714%

No Known Activations

This feature has no known activations.