INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

è¾ħ

-0.27

:center

-0.26

æĭĽåķĨ

-0.25

onne

-0.25

inkle

-0.25

 Hund

-0.24

erg

-0.24

è¾ħåĬ©

-0.24

ãĤ¼

-0.23

æŁĶè½¯

-0.23

POSITIVE LOGITS

ä¸ĵåĳĺ

0.27

 craz

0.27

procs

0.26

 encounters

0.26

stances

0.26

rias

0.26

arl

0.25

åħļæł¡

0.25

 extraction

0.24

è¹ĭ

0.24

Activations Density 0.024%

No Comments

No Known Activations