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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¢«æĬĵ

-0.29

è·¯å¾Ħ

-0.26

å¤ªå¹³æ´ĭ

-0.25

 methods

-0.25

iPad

-0.24

çļĦæĸ¹æ³ķ

-0.24

 sidewalk

-0.24

çŃĮ

-0.24

 gadgets

-0.23

ç¿»èº«

-0.23

POSITIVE LOGITS

licate

0.27

 Ð±Ð¸Ð·

0.27

ONY

0.27

 Statement

0.25

LEC

0.25

IEW

0.25

 Statements

0.25

ç¡Ĵ

0.24

ivate

0.24

 sticky

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.