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

imal

-0.28

esian

-0.27

imate

-0.26

éĿł

-0.26

ucid

-0.25

igan

-0.25

cip

-0.25

 aggregate

-0.24

estyle

-0.24

POSITIVE LOGITS

è®¾æĥ³

0.26

ä¸ĢæĬĬ

0.25

 Forward

0.25

å¦ĤæĦı

0.25

 Slots

0.24

æĤ¬

0.24

å¾ĹæĦı

0.24

implements

0.24

artner

0.24

hv

0.24

Activations Density 0.012%

No Known Activations

This feature has no known activations.