INDEX

Explanations

story

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

auf

-0.27

MLP

-0.26

 Dissertation

-0.26

DBus

-0.26

_phys

-0.25

iland

-0.24

lius

-0.24

.hl

-0.24

 uwaÅ¼

-0.24

indr

-0.23

POSITIVE LOGITS

rev

0.30

 finals

0.25

 Courier

0.25

taire

0.25

è£ģ

0.24

occ

0.24

onna

0.24

aign

0.24

 altern

0.23

 spikes

0.23

Activations Density 0.017%

story

No Comments

No Known Activations