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

agher

-0.26

 Slate

-0.26

è¯·åıĬæĹ¶

-0.24

éĴľ

-0.24

rible

-0.24

ailles

-0.24

å´Ľ

-0.24

åį«è§Ĩ

-0.24

ActionTypes

-0.23

haps

-0.23

POSITIVE LOGITS

åı£

0.29

ç³»

0.28

ibe

0.28

 exercising

0.26

#:

0.25

 bypass

0.25

uhe

0.25

scenario

0.24

 exercÃŃcio

0.24

IES

0.23

Activations Density 0.019%

No Known Activations

This feature has no known activations.