INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 arrangement

-0.29

zig

-0.28

qw

-0.26

 appar

-0.25

orage

-0.24

 struct

-0.24

pci

-0.24

 Morales

-0.23

 penal

-0.23

İ·

-0.23

POSITIVE LOGITS

geries

0.29

NIL

0.28

ophil

0.25

reso

0.25

oplevel

0.24

:'.$

0.24

isses

0.24

 Trev

0.24

 valign

0.24

ahead

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.