INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã¤mp

-0.26

èĬ

-0.25

èĢĥéªĮ

-0.24

 BrowserAnimationsModule

-0.24

áº¡p

-0.24

_$

-0.23

ãĤ¿ãĤ¤

-0.23

gnore

-0.23

nic

-0.23

__$

-0.23

POSITIVE LOGITS

åºĲ

0.27

ãĢħ

0.25

ells

0.24

infer

0.24

 vÃŃt

0.24

çļĦèº«ä»½

0.24

å²ĺ

0.24

Built

0.24

ybrid

0.24

 ÐľÐ°

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.