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

 dissertation

-0.28

åħ»æĬ¤

-0.26

æī¹éĩı

-0.26

legt

-0.25

 fetching

-0.25

 amplifier

-0.25

áº¯p

-0.25

=batch

-0.24

 keyof

-0.24

 nowhere

-0.23

POSITIVE LOGITS

pol

0.27

etrain

0.25

etable

0.25

åįĹæĸ¹

0.25

Ð¸ÑĤÐµÑĤ

0.25

åĲİ

0.24

 Rossi

0.23

lug

0.23

INGS

0.23

 Swan

0.23

Activations Density 0.008%

No Known Activations

This feature has no known activations.