INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iju

-0.30

 Keystone

-0.27

 dressed

-0.26

-legged

-0.25

=",

-0.25

ç²¾

-0.25

Specify

-0.24

facet

-0.24

 Ø§ÙĦØ§Ø®

-0.24

 --↵↵

-0.24

POSITIVE LOGITS

iversary

0.29

.pivot

0.27

SEL

0.25

 replic

0.24

 planning

0.23

otti

0.23

åıĤä¸İèĢħ

0.23

VID

0.23

_logging

0.23

çĬĬ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.