INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icer

-0.32

odings

-0.25

ixo

-0.25

mps

-0.25

æĢĿå¿µ

-0.25

èĦī

-0.24

 lodged

-0.24

ICLES

-0.24

~-

-0.24

éĩĳåĪļ

-0.23

POSITIVE LOGITS

NR

0.28

 coinc

0.28

æŃ£æĸĩ

0.26

NR

0.26

LD

0.25

Sac

0.25

ëħ¹

0.24

 Crimea

0.24

library

0.23

åº«

0.23

Activations Density 1.760%

No Known Activations

This feature has no known activations.