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

 Head

-0.29

 dÃ©p

-0.28

 suff

-0.27

Head

-0.27

 head

-0.27

é¹Ħ

-0.26

ainen

-0.25

åįķçº¯

-0.25

_head

-0.24

heads

-0.24

POSITIVE LOGITS

çĥŃéĶĢ

0.27

fans

0.26

 spons

0.25

èĢĮåĩº

0.25

argout

0.25

/ws

0.24

 Escorts

0.24

 traceback

0.24

æĶ¾åĪ°

0.24

pin

0.24

Activations Density 30.394%

No Known Activations

This feature has no known activations.