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

igli

-0.31

elon

-0.27

prop

-0.26

åĮĹæµ·

-0.25

æīģ

-0.25

èĢģå¤§

-0.25

èĦı

-0.24

istes

-0.24

çŁ©

-0.24

entes

-0.24

POSITIVE LOGITS

nee

0.26

 Below

0.26

arium

0.25

 Verification

0.25

Exp

0.24

æĶ¥

0.24

 Scan

0.24

 consistent

0.24

ClickListener

0.24

 Software

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.