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

raig

-0.24

MainThread

-0.24

æķĻä½ł

-0.23

 uncont

-0.23

astic

-0.23

èĦī

-0.23

ila

-0.23

 shedding

-0.22

 EFFECT

-0.22

 GameState

-0.22

POSITIVE LOGITS

uchs

0.26

uch

0.26

cent

0.26

OX

0.25

st

0.25

æª«

0.25

 Hack

0.24

UCH

0.24

çĨ¨

0.24

æľīæĦıæĢĿ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.