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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¼ºåĽ½

-0.29

 slicing

-0.28

 multiplication

-0.27

rex

-0.26

åĪĩéĻ¤

-0.25

æĪĳçľĭ

-0.25

iences

-0.24

ìľ¡

-0.24

outu

-0.24

 slice

-0.23

POSITIVE LOGITS

itet

0.28

à¸²à¸¡

0.26

PU

0.26

.Struct

0.26

 táº¯c

0.26

posable

0.25

æĽ³

0.25

@(

0.25

[(

0.24

upp

0.24

Activations Density 0.006%

No Comments

No Known Activations