INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÐµÐ´ÑĮ

-0.26

æ²Ļé¾Ļ

-0.26

:].

-0.25

_soft

-0.25

æ®ĸ

-0.25

åĨľåī¯

-0.24

 Liberties

-0.24

abol

-0.23

-Mail

-0.23

imat

-0.22

POSITIVE LOGITS

mp

0.24

 tower

0.24

unker

0.23

 puck

0.23

æ»ĭ

0.23

SES

0.23

ä¸įèµ·

0.23

Dup

0.23

umper

0.23

ump

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.