INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.opensource

-0.26

cplusplus

-0.25

 longer

-0.24

civ

-0.24

 Dort

-0.23

:length

-0.23

EVER

-0.22

 elong

-0.21

PerPixel

-0.21

inia

-0.21

POSITIVE LOGITS

 Âł Âł Âł Âł

0.27

èĦį

0.24

âĢ¦âĢ¦↵↵

0.23

åı¯æĺ¯

0.23

ä¸įè¯´

0.22

åĨįè¯´

0.22

(gp

0.22

 Âł Âł

0.21

ray

0.21

åį¸

0.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.