INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

éľŃ

-0.27

ICA

-0.24

streams

-0.23

lain

-0.23

icas

-0.23

ica

-0.23

.css

-0.22

.module

-0.22

iche

-0.22

Ð¸ÐºÐ°

-0.22

POSITIVE LOGITS

 sple

0.28

èĻĲ

0.27

ndl

0.25

ocol

0.25

èĤī

0.24

åħŃåĲĪ

0.24

æĮŁ

0.24

(gen

0.24

atically

0.24

Nec

0.23

Activations Density 0.025%

No Known Activations

This feature has no known activations.