INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

egin

-0.24

_ask

-0.24

 Decide

-0.24

 refere

-0.24

åĲ¯

-0.23

ingleton

-0.23

æĢķ

-0.23

èº²åľ¨

-0.23

ãĤĦãģ¯ãĤĬ

-0.23

ÙģØ§Ø±

-0.23

POSITIVE LOGITS

æľīæĿ¡ä»¶

0.28

asma

0.28

amus

0.26

IPA

0.26

_Custom

0.25

resses

0.25

{/

0.24

wow

0.24

insk

0.24

ok

0.24

Activations Density 35.853%

No Known Activations

This feature has no known activations.